Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5754 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.7931. Min Act: -0.1700
Data Index: 5096949 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.7931. Min Act: -0.1700
Data Index: 8597969 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.7618. Min Act: -0.1700
Data Index: 3362378 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6993. Min Act: -0.1700
Data Index: 578526 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6681. Min Act: -0.1700
Data Index: 6098952 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6681. Min Act: -0.1700
Data Index: 7116160 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6368. Min Act: -0.1700
Data Index: 2893228 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6368. Min Act: -0.1700
Data Index: 708324 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6368. Min Act: -0.1700
Data Index: 847051 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6368. Min Act: -0.1700
Data Index: 4273309 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6056. Min Act: -0.1700
Data Index: 4617579 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6056. Min Act: -0.1700
Data Index: 6301046 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5743. Min Act: -0.1700
Data Index: 3793726 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5743. Min Act: -0.1700
Data Index: 6174562 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5743. Min Act: -0.1700
Data Index: 4972828 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5431. Min Act: -0.1700
Data Index: 7423823 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5431. Min Act: -0.1700
Data Index: 3702292 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5431. Min Act: -0.1700
Data Index: 4337344 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5431. Min Act: -0.1700
Data Index: 763029 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5118. Min Act: -0.1700
Data Index: 6500811 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19