Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5676 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.2533. Min Act: -0.1700
Data Index: 4623419 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.2533. Min Act: -0.1700
Data Index: 8113966 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.1595. Min Act: -0.1700
Data Index: 1228360 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.1283. Min Act: -0.1700
Data Index: 5301794 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.1283. Min Act: -0.1700
Data Index: 3643317 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0970. Min Act: -0.1700
Data Index: 8120276 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0658. Min Act: -0.1700
Data Index: 6783291 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0345. Min Act: -0.1700
Data Index: 216280 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0345. Min Act: -0.1700
Data Index: 7910710 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0345. Min Act: -0.1700
Data Index: 78393 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0033. Min Act: -0.1700
Data Index: 2233635 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0033. Min Act: -0.1700
Data Index: 727079 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0345. Min Act: -0.1700
Data Index: 3991181 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0033. Min Act: -0.1700
Data Index: 1952915 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4472193 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0033. Min Act: -0.1700
Data Index: 5467232 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0033. Min Act: -0.1700
Data Index: 7942256 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2533. Min Range: -5.2533
Max Act: 5.0033. Min Act: -0.1700
Data Index: 5595211 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9720. Min Act: -0.1700
Data Index: 6483957 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2533. Min Range: -5.2533
Max Act: 4.9720. Min Act: -0.1700
Data Index: 286262 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19