Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2035 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2091. Min Range: -8.2091
Max Act: 8.2091. Min Act: -0.1700
Data Index: 4607679 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2091. Min Range: -8.2091
Max Act: 8.2091. Min Act: -0.1700
Data Index: 5461744 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2091. Min Range: -8.2091
Max Act: 8.2091. Min Act: -0.1700
Data Index: 2754875 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2091. Min Range: -8.2091
Max Act: 8.0841. Min Act: -0.1700
Data Index: 7105956 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2091. Min Range: -8.2091
Max Act: 8.0841. Min Act: -0.1700
Data Index: 5124956 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.9591. Min Act: -0.1700
Data Index: 7459583 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2091. Min Range: -8.2091
Max Act: 8.0216. Min Act: -0.1700
Data Index: 8154914 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.9591. Min Act: -0.1700
Data Index: 5830093 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.9591. Min Act: -0.1700
Data Index: 6231314 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8966. Min Act: -0.1700
Data Index: 7408457 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8966. Min Act: -0.1700
Data Index: 2191717 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8966. Min Act: -0.1700
Data Index: 735411 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8966. Min Act: -0.1700
Data Index: 3526430 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8341. Min Act: -0.1700
Data Index: 4219045 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8341. Min Act: -0.1700
Data Index: 7278747 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.7716. Min Act: -0.1700
Data Index: 2982075 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8341. Min Act: -0.1700
Data Index: 3231720 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8341. Min Act: -0.1700
Data Index: 7515472 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8341. Min Act: -0.1700
Data Index: 6016621 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2091. Min Range: -8.2091
Max Act: 7.8341. Min Act: -0.1700
Data Index: 4073520 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19