Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 988 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.7181. Min Act: -0.1700
Data Index: 6010795 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.5460. Min Act: -0.1700
Data Index: 1356501 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4990. Min Act: -0.1700
Data Index: 6230120 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4677. Min Act: -0.1700
Data Index: 3562262 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4677. Min Act: -0.1700
Data Index: 8596014 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4520. Min Act: -0.1700
Data Index: 5398199 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4364. Min Act: -0.1700
Data Index: 1715198 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4207. Min Act: -0.1700
Data Index: 7686033 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4207. Min Act: -0.1700
Data Index: 5072448 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.4050. Min Act: -0.1700
Data Index: 8044178 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3893. Min Act: -0.1700
Data Index: 4438635 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3893. Min Act: -0.1700
Data Index: 4963597 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3893. Min Act: -0.1700
Data Index: 4922573 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3893. Min Act: -0.1700
Data Index: 145764 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3736. Min Act: -0.1700
Data Index: 696062 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3736. Min Act: -0.1700
Data Index: 5161833 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3736. Min Act: -0.1700
Data Index: 1213556 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3580. Min Act: -0.1700
Data Index: 5993464 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3266. Min Act: -0.1700
Data Index: 8372002 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7181. Min Range: -3.7181
Max Act: 3.3423. Min Act: -0.1700
Data Index: 6329209 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19