Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.3587. Min Act: -0.1700
Data Index: 4703207 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.2962. Min Act: -0.1700
Data Index: 5398803 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7893733 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.2025. Min Act: -0.1700
Data Index: 1583534 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7391771 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.1400. Min Act: -0.1700
Data Index: 2614607 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.1400. Min Act: -0.1700
Data Index: 7989568 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.0462. Min Act: -0.1700
Data Index: 1341839 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.0462. Min Act: -0.1700
Data Index: 4712761 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.0462. Min Act: -0.1700
Data Index: 4004924 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.0462. Min Act: -0.1700
Data Index: 231389 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3587. Min Range: -4.3587
Max Act: 4.0462. Min Act: -0.1700
Data Index: 3116911 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9837. Min Act: -0.1700
Data Index: 3577498 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9837. Min Act: -0.1700
Data Index: 8386431 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9837. Min Act: -0.1700
Data Index: 1317407 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9837. Min Act: -0.1700
Data Index: 3915677 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9837. Min Act: -0.1700
Data Index: 4494580 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9837. Min Act: -0.1700
Data Index: 7810131 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9524. Min Act: -0.1700
Data Index: 6215255 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3587. Min Range: -4.3587
Max Act: 3.9212. Min Act: -0.1700
Data Index: 1988486 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19