Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2248 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.7620. Min Act: -0.1700
Data Index: 8001679 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.7534. Min Act: -0.1700
Data Index: 8730639 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.7448. Min Act: -0.1700
Data Index: 1334947 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.7188. Min Act: -0.1700
Data Index: 361893 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.7188. Min Act: -0.1700
Data Index: 1019118 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.7015. Min Act: -0.1700
Data Index: 4350416 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6928. Min Act: -0.1699
Data Index: 5502566 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.7015. Min Act: -0.1699
Data Index: 3245254 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6928. Min Act: -0.1700
Data Index: 5517043 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6841. Min Act: -0.1699
Data Index: 2063630 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6755. Min Act: -0.1697
Data Index: 5736684 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6755. Min Act: -0.1700
Data Index: 3356072 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6668. Min Act: -0.1698
Data Index: 2318198 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6668. Min Act: -0.1700
Data Index: 5703229 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6755. Min Act: -0.1699
Data Index: 7511578 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6581. Min Act: -0.1700
Data Index: 7791618 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6581. Min Act: -0.1700
Data Index: 7241805 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6494. Min Act: -0.1699
Data Index: 749001 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6668. Min Act: -0.1700
Data Index: 7328745 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7620. Min Range: -1.7620
Max Act: 1.6581. Min Act: -0.1700
Data Index: 7964061 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19