Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.5892. Min Act: -0.1700
Data Index: 8774111 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4796. Min Act: -0.1700
Data Index: 7372555 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4796. Min Act: -0.1700
Data Index: 2706381 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4796. Min Act: -0.1700
Data Index: 275100 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4326. Min Act: -0.1700
Data Index: 7900256 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4483. Min Act: -0.1700
Data Index: 2896041 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4483. Min Act: -0.1700
Data Index: 8587494 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4326. Min Act: -0.1700
Data Index: 5491740 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4169. Min Act: -0.1700
Data Index: 4509640 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4013. Min Act: -0.1700
Data Index: 2973480 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.4013. Min Act: -0.1700
Data Index: 5980233 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3699. Min Act: -0.1700
Data Index: 4896536 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3699. Min Act: -0.1700
Data Index: 6103594 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3699. Min Act: -0.1700
Data Index: 5767458 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3542. Min Act: -0.1700
Data Index: 6268814 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3542. Min Act: -0.1700
Data Index: 5529338 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3542. Min Act: -0.1700
Data Index: 2355055 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3542. Min Act: -0.1700
Data Index: 1175867 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3385. Min Act: -0.1700
Data Index: 8154963 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5892. Min Range: -3.5892
Max Act: 3.3228. Min Act: -0.1700
Data Index: 5005727 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19