Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6100 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.6402. Min Act: -0.1700
Data Index: 7904624 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.4527. Min Act: -0.1700
Data Index: 4454684 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.3589. Min Act: -0.1700
Data Index: 4519422 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.4214. Min Act: -0.1700
Data Index: 4730411 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.1089. Min Act: -0.1700
Data Index: 2221582 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.1089. Min Act: -0.1700
Data Index: 673617 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.0777. Min Act: -0.1700
Data Index: 8565752 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6402. Min Range: -7.6402
Max Act: 7.0464. Min Act: -0.1700
Data Index: 3069538 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.9214. Min Act: -0.1700
Data Index: 4971298 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.9214. Min Act: -0.1700
Data Index: 2755419 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.9214. Min Act: -0.1700
Data Index: 6459658 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8902. Min Act: -0.1700
Data Index: 1832487 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8902. Min Act: -0.1700
Data Index: 7348096 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8902. Min Act: -0.1700
Data Index: 3323273 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8589. Min Act: -0.1700
Data Index: 7850243 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8589. Min Act: -0.1700
Data Index: 704663 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8277. Min Act: -0.1700
Data Index: 3316873 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8589. Min Act: -0.1700
Data Index: 1799275 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8589. Min Act: -0.1700
Data Index: 1136248 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6402. Min Range: -7.6402
Max Act: 6.8589. Min Act: -0.1700
Data Index: 1012531 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19