Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0873. Min Range: -5.0873
Max Act: 5.0873. Min Act: -0.1700
Data Index: 7515773 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0873. Min Range: -5.0873
Max Act: 5.0248. Min Act: -0.1700
Data Index: 2079483 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.9623. Min Act: -0.1700
Data Index: 2272895 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.9623. Min Act: -0.1700
Data Index: 328978 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.9623. Min Act: -0.1700
Data Index: 3657069 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.9623. Min Act: -0.1700
Data Index: 4893119 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8998. Min Act: -0.1700
Data Index: 7898663 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8685. Min Act: -0.1700
Data Index: 2416428 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8685. Min Act: -0.1700
Data Index: 355571 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8373. Min Act: -0.1700
Data Index: 2580424 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8373. Min Act: -0.1700
Data Index: 6197580 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8373. Min Act: -0.1700
Data Index: 1516316 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8373. Min Act: -0.1700
Data Index: 5546351 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8373. Min Act: -0.1700
Data Index: 3657615 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8373. Min Act: -0.1700
Data Index: 6801694 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8060. Min Act: -0.1700
Data Index: 6730205 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.8373. Min Act: -0.1700
Data Index: 2726873 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.7748. Min Act: -0.1700
Data Index: 1378210 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.7748. Min Act: -0.1700
Data Index: 4185671 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0873. Min Range: -5.0873
Max Act: 4.7748. Min Act: -0.1700
Data Index: 5699162 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19