Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.3438. Min Act: -0.1700
Data Index: 6746063 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2615. Min Act: -0.1700
Data Index: 7283043 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2780. Min Act: -0.1700
Data Index: 6588023 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2615. Min Act: -0.1700
Data Index: 2582535 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2450. Min Act: -0.1700
Data Index: 2725344 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2450. Min Act: -0.1700
Data Index: 2602668 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2450. Min Act: -0.1700
Data Index: 5631245 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2450. Min Act: -0.1700
Data Index: 7391087 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2285. Min Act: -0.1700
Data Index: 4699384 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2285. Min Act: -0.1700
Data Index: 3501531 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.2285. Min Act: -0.1700
Data Index: 8710513 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1953. Min Act: -0.1700
Data Index: 4642176 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1953. Min Act: -0.1700
Data Index: 5487723 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1787. Min Act: -0.1700
Data Index: 5749036 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1953. Min Act: -0.1700
Data Index: 6585048 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1787. Min Act: -0.1700
Data Index: 4235660 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1621. Min Act: -0.1700
Data Index: 1163393 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1454. Min Act: -0.1700
Data Index: 3216536 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1621. Min Act: -0.1700
Data Index: 8558014 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3438. Min Range: -2.3438
Max Act: 2.1454. Min Act: -0.1700
Data Index: 5352247 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19