Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1416 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0385. Min Act: -0.1700
Data Index: 6207985 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0385. Min Act: -0.1700
Data Index: 7298187 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0385. Min Act: -0.1700
Data Index: 76141 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0072. Min Act: -0.1700
Data Index: 6748318 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0072. Min Act: -0.1700
Data Index: 4419794 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0072. Min Act: -0.1700
Data Index: 4404327 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0072. Min Act: -0.1700
Data Index: 7596103 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0072. Min Act: -0.1700
Data Index: 419462 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 3897331 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 3484742 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9447. Min Act: -0.1700
Data Index: 1112242 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 4416638 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0385. Min Range: -4.0385
Max Act: 4.0072. Min Act: -0.1700
Data Index: 76140 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 211845 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 76138 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 5677843 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 6049630 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 338618 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 2242352 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0385. Min Range: -4.0385
Max Act: 3.9760. Min Act: -0.1700
Data Index: 408710 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19