Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 319 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0318. Min Range: -4.0318
Max Act: 4.0318. Min Act: -0.1700
Data Index: 2094963 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.9380. Min Act: -0.1700
Data Index: 4194566 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.9692. Min Act: -0.1700
Data Index: 8615425 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.8755. Min Act: -0.1700
Data Index: 4316124 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.8755. Min Act: -0.1700
Data Index: 7737928 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.8129. Min Act: -0.1700
Data Index: 4052911 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7816. Min Act: -0.1700
Data Index: 8159220 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7816. Min Act: -0.1700
Data Index: 3297216 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.8129. Min Act: -0.1700
Data Index: 4055714 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7816. Min Act: -0.1700
Data Index: 4202083 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7504. Min Act: -0.1700
Data Index: 1411037 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7504. Min Act: -0.1700
Data Index: 4832852 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7504. Min Act: -0.1700
Data Index: 5113575 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7191. Min Act: -0.1700
Data Index: 4719751 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7191. Min Act: -0.1700
Data Index: 8324430 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.6878. Min Act: -0.1700
Data Index: 2094962 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7191. Min Act: -0.1700
Data Index: 4719750 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.6878. Min Act: -0.1700
Data Index: 2137541 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.6878. Min Act: -0.1700
Data Index: 2370100 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0318. Min Range: -4.0318
Max Act: 3.7191. Min Act: -0.1700
Data Index: 638338 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19