Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.9069. Min Act: -0.1700
Data Index: 8677514 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8385. Min Act: -0.1700
Data Index: 6144520 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8385. Min Act: -0.1700
Data Index: 1380244 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8214. Min Act: -0.1700
Data Index: 7197579 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8042. Min Act: -0.1700
Data Index: 5472477 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8214. Min Act: -0.1700
Data Index: 2470915 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8042. Min Act: -0.1700
Data Index: 8349021 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8214. Min Act: -0.1700
Data Index: 1563375 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7870. Min Act: -0.1700
Data Index: 2296686 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.8214. Min Act: -0.1700
Data Index: 1450921 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7870. Min Act: -0.1700
Data Index: 6928441 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7697. Min Act: -0.1700
Data Index: 658777 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7870. Min Act: -0.1700
Data Index: 4049139 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7870. Min Act: -0.1700
Data Index: 5699783 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7870. Min Act: -0.1698
Data Index: 19186 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7870. Min Act: -0.1700
Data Index: 2379318 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7697. Min Act: -0.1700
Data Index: 1380243 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7697. Min Act: -0.1700
Data Index: 2805126 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7870. Min Act: -0.1700
Data Index: 3114135 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9069. Min Range: -1.9069
Max Act: 1.7697. Min Act: -0.1700
Data Index: 7060981 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19