Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4949. Min Act: -0.1700
Data Index: 2300331 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4787. Min Act: -0.1700
Data Index: 6595057 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4949. Min Act: -0.1700
Data Index: 3534875 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4624. Min Act: -0.1700
Data Index: 2128298 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4462. Min Act: -0.1700
Data Index: 7012488 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4462. Min Act: -0.1700
Data Index: 540265 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4136. Min Act: -0.1700
Data Index: 2817333 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4462. Min Act: -0.1700
Data Index: 4742817 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4462. Min Act: -0.1700
Data Index: 1427658 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4136. Min Act: -0.1700
Data Index: 3951413 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3973. Min Act: -0.1700
Data Index: 1407211 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.4299. Min Act: -0.1700
Data Index: 3277287 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3973. Min Act: -0.1700
Data Index: 6853832 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3810. Min Act: -0.1700
Data Index: 5660987 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3810. Min Act: -0.1700
Data Index: 5366343 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3810. Min Act: -0.1700
Data Index: 6798013 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3810. Min Act: -0.1700
Data Index: 1421151 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3810. Min Act: -0.1700
Data Index: 2466623 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3973. Min Act: -0.1700
Data Index: 5396496 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4949. Min Range: -2.4949
Max Act: 2.3482. Min Act: -0.1700
Data Index: 5306927 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19