Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2123 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.7125. Min Act: -0.1700
Data Index: 109976 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4777. Min Act: -0.1700
Data Index: 1562982 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4620. Min Act: -0.1700
Data Index: 3216503 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4620. Min Act: -0.1700
Data Index: 2813349 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4307. Min Act: -0.1700
Data Index: 1103073 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4307. Min Act: -0.1700
Data Index: 4549817 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4620. Min Act: -0.1700
Data Index: 1683481 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4464. Min Act: -0.1700
Data Index: 2247140 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4464. Min Act: -0.1700
Data Index: 4319091 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4307. Min Act: -0.1700
Data Index: 2648362 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4464. Min Act: -0.1700
Data Index: 4326533 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4150. Min Act: -0.1700
Data Index: 217851 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.4307. Min Act: -0.1700
Data Index: 3250628 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.3837. Min Act: -0.1700
Data Index: 1142732 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.3837. Min Act: -0.1700
Data Index: 5053309 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.3680. Min Act: -0.1700
Data Index: 2678901 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.3837. Min Act: -0.1700
Data Index: 391476 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.3523. Min Act: -0.1700
Data Index: 7902255 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.3366. Min Act: -0.1700
Data Index: 8081244 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.3366. Min Act: -0.1700
Data Index: 1045165 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19