Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0336. Min Range: -8.0336
Max Act: 8.0336. Min Act: -0.1700
Data Index: 6324763 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.9711. Min Act: -0.1700
Data Index: 4581935 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.9086. Min Act: -0.1700
Data Index: 4421490 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.9086. Min Act: -0.1700
Data Index: 30567 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.7523. Min Act: -0.1700
Data Index: 177453 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.6898. Min Act: -0.1700
Data Index: 3833119 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.6586. Min Act: -0.1700
Data Index: 1737794 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.6586. Min Act: -0.1700
Data Index: 6336847 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.6586. Min Act: -0.1700
Data Index: 2619933 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.5961. Min Act: -0.1700
Data Index: 1151067 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.5961. Min Act: -0.1700
Data Index: 8830017 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.5961. Min Act: -0.1700
Data Index: 3751958 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.5336. Min Act: -0.1700
Data Index: 123274 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.4711. Min Act: -0.1700
Data Index: 879097 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.4398. Min Act: -0.1700
Data Index: 1570692 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.4398. Min Act: -0.1700
Data Index: 5540367 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.4086. Min Act: -0.1700
Data Index: 7950319 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.4086. Min Act: -0.1700
Data Index: 6691495 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.4086. Min Act: -0.1700
Data Index: 1972577 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0336. Min Range: -8.0336
Max Act: 7.4086. Min Act: -0.1700
Data Index: 1316883 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19