Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 628 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.2223. Min Act: -0.1700
Data Index: 6080397 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1909. Min Act: -0.1700
Data Index: 8435383 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1909. Min Act: -0.1700
Data Index: 1672562 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1594. Min Act: -0.1700
Data Index: 1319335 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1279. Min Act: -0.1700
Data Index: 7006802 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1437. Min Act: -0.1700
Data Index: 6310551 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1121. Min Act: -0.1700
Data Index: 4147665 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1121. Min Act: -0.1700
Data Index: 6347332 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.1121. Min Act: -0.1700
Data Index: 327027 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0491. Min Act: -0.1700
Data Index: 2982855 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0649. Min Act: -0.1700
Data Index: 6565167 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0491. Min Act: -0.1700
Data Index: 3140529 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0491. Min Act: -0.1700
Data Index: 7555707 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0491. Min Act: -0.1700
Data Index: 6452883 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0333. Min Act: -0.1700
Data Index: 1686586 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0491. Min Act: -0.1700
Data Index: 2675981 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0175. Min Act: -0.1700
Data Index: 5468036 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0333. Min Act: -0.1700
Data Index: 8140201 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0175. Min Act: -0.1700
Data Index: 544367 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2223. Min Range: -3.2223
Max Act: 3.0175. Min Act: -0.1700
Data Index: 1064068 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19