Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0181. Min Range: -6.0181
Max Act: 6.0181. Min Act: -0.1700
Data Index: 6323415 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.7056. Min Act: -0.1700
Data Index: 7387402 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.7056. Min Act: -0.1700
Data Index: 2758255 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.6744. Min Act: -0.1700
Data Index: 1639486 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.6744. Min Act: -0.1700
Data Index: 7662331 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.6744. Min Act: -0.1700
Data Index: 8713813 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.5806. Min Act: -0.1700
Data Index: 1023202 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.5181. Min Act: -0.1700
Data Index: 3411363 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.5181. Min Act: -0.1700
Data Index: 7226397 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.5181. Min Act: -0.1700
Data Index: 3909389 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4869. Min Act: -0.1700
Data Index: 4228234 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4869. Min Act: -0.1700
Data Index: 4390394 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4869. Min Act: -0.1700
Data Index: 890629 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4556. Min Act: -0.1700
Data Index: 5599455 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4556. Min Act: -0.1700
Data Index: 70560 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4556. Min Act: -0.1700
Data Index: 4541482 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4556. Min Act: -0.1700
Data Index: 3623861 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4556. Min Act: -0.1700
Data Index: 5411058 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.4556. Min Act: -0.1700
Data Index: 1004618 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0181. Min Range: -6.0181
Max Act: 5.3931. Min Act: -0.1700
Data Index: 5255847 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19