Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.3261. Min Act: -0.1700
Data Index: 2419601 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2947. Min Act: -0.1700
Data Index: 3932819 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2633. Min Act: -0.1700
Data Index: 1845007 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2318. Min Act: -0.1700
Data Index: 7074323 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2004. Min Act: -0.1700
Data Index: 3961698 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2476. Min Act: -0.1700
Data Index: 4927075 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2004. Min Act: -0.1700
Data Index: 5584550 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2318. Min Act: -0.1700
Data Index: 409985 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2161. Min Act: -0.1700
Data Index: 3880054 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2004. Min Act: -0.1700
Data Index: 2575441 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2004. Min Act: -0.1700
Data Index: 3211731 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.1847. Min Act: -0.1700
Data Index: 4649216 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.1847. Min Act: -0.1700
Data Index: 5487015 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2004. Min Act: -0.1700
Data Index: 4006 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.1847. Min Act: -0.1700
Data Index: 3457355 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.2161. Min Act: -0.1700
Data Index: 3117494 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.1689. Min Act: -0.1700
Data Index: 2128428 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.1847. Min Act: -0.1700
Data Index: 6067038 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.1217. Min Act: -0.1700
Data Index: 2251170 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3261. Min Range: -3.3261
Max Act: 3.1847. Min Act: -0.1700
Data Index: 4210497 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19