Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4753 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.7355. Min Act: -0.1700
Data Index: 1692192 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.7043. Min Act: -0.1700
Data Index: 828706 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.6730. Min Act: -0.1700
Data Index: 2909835 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.6418. Min Act: -0.1700
Data Index: 1224129 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.6418. Min Act: -0.1700
Data Index: 8348843 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.6105. Min Act: -0.1700
Data Index: 6755363 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.5480. Min Act: -0.1700
Data Index: 8804981 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.5168. Min Act: -0.1700
Data Index: 6787812 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.5168. Min Act: -0.1700
Data Index: 4069306 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.4855. Min Act: -0.1700
Data Index: 2612674 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.4543. Min Act: -0.1700
Data Index: 7642084 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.4543. Min Act: -0.1700
Data Index: 636053 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.4543. Min Act: -0.1700
Data Index: 428029 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.4230. Min Act: -0.1700
Data Index: 7924186 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.3918. Min Act: -0.1700
Data Index: 8585095 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.4230. Min Act: -0.1700
Data Index: 3065417 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.3918. Min Act: -0.1700
Data Index: 1403638 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.3918. Min Act: -0.1700
Data Index: 1497216 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.3918. Min Act: -0.1700
Data Index: 5323479 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7355. Min Range: -6.7355
Max Act: 6.3605. Min Act: -0.1700
Data Index: 8754620 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19