Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 260 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2625. Min Range: -11.2625
Max Act: 11.2625. Min Act: -0.1700
Data Index: 2519588 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2625. Min Range: -11.2625
Max Act: 11.2625. Min Act: -0.1700
Data Index: 1935002 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2625. Min Range: -11.2625
Max Act: 11.0125. Min Act: -0.1700
Data Index: 4924087 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2625. Min Range: -11.2625
Max Act: 11.0750. Min Act: -0.1700
Data Index: 6849909 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2625. Min Range: -11.2625
Max Act: 11.0125. Min Act: -0.1700
Data Index: 4657738 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.9500. Min Act: -0.1700
Data Index: 8675802 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.8875. Min Act: -0.1700
Data Index: 2556057 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.8250. Min Act: -0.1700
Data Index: 6092511 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.8250. Min Act: -0.1700
Data Index: 1961278 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.8250. Min Act: -0.1700
Data Index: 2406822 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7625. Min Act: -0.1700
Data Index: 1645131 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7625. Min Act: -0.1700
Data Index: 3245885 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7625. Min Act: -0.1700
Data Index: 3201877 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7625. Min Act: -0.1700
Data Index: 2981240 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7625. Min Act: -0.1700
Data Index: 7375632 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7625. Min Act: -0.1700
Data Index: 4849376 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7000. Min Act: -0.1700
Data Index: 5442415 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.6375. Min Act: -0.1700
Data Index: 3242735 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7000. Min Act: -0.1700
Data Index: 3549341 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2625. Min Range: -11.2625
Max Act: 10.7000. Min Act: -0.1700
Data Index: 2119635 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19