Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.6313. Min Act: -0.1700
Data Index: 1130082 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.5688. Min Act: -0.1700
Data Index: 3486327 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.5376. Min Act: -0.1700
Data Index: 2235589 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.5376. Min Act: -0.1700
Data Index: 2989969 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.5376. Min Act: -0.1700
Data Index: 2845105 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.5063. Min Act: -0.1700
Data Index: 411576 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.5063. Min Act: -0.1700
Data Index: 7631964 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 3045500 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 6868006 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 8122774 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 567769 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 7581749 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 7432614 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 5848537 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 5157952 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4438. Min Act: -0.1700
Data Index: 4400123 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4438. Min Act: -0.1700
Data Index: 2308779 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 3724131 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4751. Min Act: -0.1700
Data Index: 3496194 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6313. Min Range: -4.6313
Max Act: 4.4438. Min Act: -0.1700
Data Index: 2174113 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19