Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.2316. Min Act: -0.1700
Data Index: 6866402 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.1611. Min Act: -0.1700
Data Index: 5215350 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.1611. Min Act: -0.1697
Data Index: 5217973 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.1611. Min Act: -0.1700
Data Index: 7822718 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.1260. Min Act: -0.1700
Data Index: 5217981 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.1260. Min Act: -0.1700
Data Index: 8329271 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0910. Min Act: -0.1694
Data Index: 3567110 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1700
Data Index: 6119460 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0910. Min Act: -0.1691
Data Index: 7159718 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0910. Min Act: -0.1697
Data Index: 4445764 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0910. Min Act: -0.1698
Data Index: 6866400 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1699
Data Index: 8437579 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1700
Data Index: 687905 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0560. Min Act: -0.1700
Data Index: 6791488 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0560. Min Act: -0.1700
Data Index: 3142267 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1700
Data Index: 8518307 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1700
Data Index: 3870094 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1694
Data Index: 74804 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1700
Data Index: 8715198 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2316. Min Range: -1.2316
Max Act: 1.0735. Min Act: -0.1700
Data Index: 2666559 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19