Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 955 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.1161. Min Act: -0.1700
Data Index: 3290595 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0848. Min Act: -0.1700
Data Index: 7149192 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0536. Min Act: -0.1700
Data Index: 6132677 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0536. Min Act: -0.1700
Data Index: 837707 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0223. Min Act: -0.1700
Data Index: 8329578 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0536. Min Act: -0.1700
Data Index: 212775 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0536. Min Act: -0.1700
Data Index: 5503791 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0536. Min Act: -0.1700
Data Index: 5358321 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0536. Min Act: -0.1700
Data Index: 6364093 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0536. Min Act: -0.1700
Data Index: 858777 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0223. Min Act: -0.1700
Data Index: 6968971 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0223. Min Act: -0.1700
Data Index: 5489546 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0223. Min Act: -0.1700
Data Index: 6689807 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1161. Min Range: -5.1161
Max Act: 4.9911. Min Act: -0.1700
Data Index: 8219248 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1161. Min Range: -5.1161
Max Act: 4.9911. Min Act: -0.1700
Data Index: 4661667 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0223. Min Act: -0.1700
Data Index: 6086527 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0223. Min Act: -0.1700
Data Index: 1280582 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1161. Min Range: -5.1161
Max Act: 5.0223. Min Act: -0.1700
Data Index: 2180660 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1161. Min Range: -5.1161
Max Act: 4.9911. Min Act: -0.1700
Data Index: 3361443 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1161. Min Range: -5.1161
Max Act: 4.9911. Min Act: -0.1700
Data Index: 3453159 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19