Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.8649. Min Act: -0.1700
Data Index: 6892650 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.8649. Min Act: -0.1700
Data Index: 1663094 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.8336. Min Act: -0.1700
Data Index: 3482887 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.7711. Min Act: -0.1700
Data Index: 8183515 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.7711. Min Act: -0.1700
Data Index: 4902919 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.7086. Min Act: -0.1700
Data Index: 5217784 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.6461. Min Act: -0.1700
Data Index: 119663 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.6149. Min Act: -0.1700
Data Index: 819515 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.5836. Min Act: -0.1700
Data Index: 6409041 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.5836. Min Act: -0.1700
Data Index: 5202550 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.5836. Min Act: -0.1700
Data Index: 1589743 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.5211. Min Act: -0.1700
Data Index: 3322225 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.5524. Min Act: -0.1700
Data Index: 5248510 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.4899. Min Act: -0.1700
Data Index: 6761618 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.4586. Min Act: -0.1700
Data Index: 8404287 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.4899. Min Act: -0.1700
Data Index: 5130028 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.5211. Min Act: -0.1700
Data Index: 5625448 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.4899. Min Act: -0.1700
Data Index: 3547884 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.4899. Min Act: -0.1700
Data Index: 1104656 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8649. Min Range: -5.8649
Max Act: 5.4899. Min Act: -0.1700
Data Index: 4501550 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19