Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.6220. Min Act: -0.1700
Data Index: 3036104 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3095. Min Act: -0.1700
Data Index: 3036102 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.2470. Min Act: -0.1700
Data Index: 5751177 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.2470. Min Act: -0.1700
Data Index: 5895046 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.2158. Min Act: -0.1700
Data Index: 3036101 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1845. Min Act: -0.1700
Data Index: 7528500 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1845. Min Act: -0.1700
Data Index: 3948769 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1533. Min Act: -0.1700
Data Index: 8314927 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1533. Min Act: -0.1700
Data Index: 7882452 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1220. Min Act: -0.1700
Data Index: 4809231 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1533. Min Act: -0.1700
Data Index: 3036103 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1533. Min Act: -0.1700
Data Index: 184149 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1220. Min Act: -0.1700
Data Index: 8783444 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1220. Min Act: -0.1700
Data Index: 5992617 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1220. Min Act: -0.1700
Data Index: 7269942 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.1220. Min Act: -0.1700
Data Index: 5869869 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.0907. Min Act: -0.1700
Data Index: 6046389 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.0907. Min Act: -0.1700
Data Index: 3806243 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.0907. Min Act: -0.1700
Data Index: 248541 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.0907. Min Act: -0.1700
Data Index: 7293885 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19