Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6055 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.8084. Min Act: -0.1700
Data Index: 8560145 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.7771. Min Act: -0.1700
Data Index: 7298599 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.7146. Min Act: -0.1700
Data Index: 8026217 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.4646. Min Act: -0.1700
Data Index: 8571689 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.4646. Min Act: -0.1700
Data Index: 8366986 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.4334. Min Act: -0.1700
Data Index: 6492290 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.4021. Min Act: -0.1700
Data Index: 3259216 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.3396. Min Act: -0.1700
Data Index: 2304924 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.3396. Min Act: -0.1700
Data Index: 7321181 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.3084. Min Act: -0.1700
Data Index: 8106101 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.3084. Min Act: -0.1700
Data Index: 6343572 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.3084. Min Act: -0.1700
Data Index: 8134370 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2771. Min Act: -0.1700
Data Index: 938705 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2771. Min Act: -0.1700
Data Index: 951543 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2771. Min Act: -0.1700
Data Index: 7633231 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2459. Min Act: -0.1700
Data Index: 3724649 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2459. Min Act: -0.1700
Data Index: 6943553 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2459. Min Act: -0.1700
Data Index: 3390877 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2146. Min Act: -0.1700
Data Index: 2382027 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8084. Min Range: -5.8084
Max Act: 5.2459. Min Act: -0.1700
Data Index: 8547717 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19