Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4627 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.3846. Min Act: -0.1700
Data Index: 1251126 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.3533. Min Act: -0.1700
Data Index: 6991480 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.3533. Min Act: -0.1700
Data Index: 7805590 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.3221. Min Act: -0.1700
Data Index: 819435 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.3221. Min Act: -0.1700
Data Index: 4686767 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.2596. Min Act: -0.1700
Data Index: 1482548 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.2908. Min Act: -0.1700
Data Index: 8790777 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.2596. Min Act: -0.1700
Data Index: 3454 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.2283. Min Act: -0.1700
Data Index: 3353138 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.2283. Min Act: -0.1700
Data Index: 3808352 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.2283. Min Act: -0.1700
Data Index: 4248462 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1971. Min Act: -0.1700
Data Index: 3029059 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1971. Min Act: -0.1700
Data Index: 7099361 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1971. Min Act: -0.1700
Data Index: 6397302 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1971. Min Act: -0.1700
Data Index: 3808360 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1971. Min Act: -0.1700
Data Index: 2023097 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1658. Min Act: -0.1700
Data Index: 264361 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1658. Min Act: -0.1699
Data Index: 5626286 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1346. Min Act: -0.1700
Data Index: 3219184 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3846. Min Range: -5.3846
Max Act: 5.1658. Min Act: -0.1700
Data Index: 6763189 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19