Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 535 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0281. Min Range: -4.0281
Max Act: 4.0281. Min Act: -0.1700
Data Index: 2008787 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.9656. Min Act: -0.1700
Data Index: 4777093 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.9031. Min Act: -0.1700
Data Index: 8243758 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.8093. Min Act: -0.1700
Data Index: 6938221 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.8093. Min Act: -0.1700
Data Index: 4634586 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.7311. Min Act: -0.1700
Data Index: 6765120 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.7154. Min Act: -0.1700
Data Index: 7025201 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.7154. Min Act: -0.1700
Data Index: 3813248 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6998. Min Act: -0.1700
Data Index: 8593580 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.7154. Min Act: -0.1700
Data Index: 2008791 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6842. Min Act: -0.1700
Data Index: 5696537 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6685. Min Act: -0.1700
Data Index: 2943560 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6685. Min Act: -0.1700
Data Index: 5822127 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6529. Min Act: -0.1700
Data Index: 6020352 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6372. Min Act: -0.1700
Data Index: 1021469 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6216. Min Act: -0.1700
Data Index: 5267145 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6059. Min Act: -0.1700
Data Index: 876736 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6059. Min Act: -0.1700
Data Index: 7830926 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.6059. Min Act: -0.1700
Data Index: 4997480 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0281. Min Range: -4.0281
Max Act: 3.5903. Min Act: -0.1700
Data Index: 4349540 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19