Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4919 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.7064. Min Act: -0.1700
Data Index: 3898027 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.6282. Min Act: -0.1700
Data Index: 6996704 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5969. Min Act: -0.1700
Data Index: 5785162 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5969. Min Act: -0.1700
Data Index: 312002 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5656. Min Act: -0.1700
Data Index: 1878469 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5499. Min Act: -0.1700
Data Index: 4394734 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5499. Min Act: -0.1700
Data Index: 1259943 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5186. Min Act: -0.1700
Data Index: 2456800 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5186. Min Act: -0.1700
Data Index: 5384017 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4873. Min Act: -0.1700
Data Index: 1490961 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.5030. Min Act: -0.1700
Data Index: 4112919 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4716. Min Act: -0.1700
Data Index: 7290817 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4560. Min Act: -0.1700
Data Index: 8317575 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4560. Min Act: -0.1700
Data Index: 3105781 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4560. Min Act: -0.1700
Data Index: 3995437 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4716. Min Act: -0.1700
Data Index: 4427979 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4560. Min Act: -0.1700
Data Index: 7274850 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4403. Min Act: -0.1700
Data Index: 2726757 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4403. Min Act: -0.1700
Data Index: 539601 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7064. Min Range: -3.7064
Max Act: 3.4403. Min Act: -0.1700
Data Index: 2195913 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19