Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5987 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.6777. Min Act: -0.1700
Data Index: 5747140 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.3652. Min Act: -0.1700
Data Index: 5265506 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.2402. Min Act: -0.1700
Data Index: 2320304 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.2402. Min Act: -0.1700
Data Index: 1702214 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.1152. Min Act: -0.1700
Data Index: 4846166 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.1152. Min Act: -0.1700
Data Index: 3430449 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.1152. Min Act: -0.1700
Data Index: 3170754 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6777. Min Range: -9.6777
Max Act: 9.0527. Min Act: -0.1700
Data Index: 5116939 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.9902. Min Act: -0.1700
Data Index: 1573949 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.9902. Min Act: -0.1700
Data Index: 5814286 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.9277. Min Act: -0.1700
Data Index: 4449025 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.9277. Min Act: -0.1700
Data Index: 4434111 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.9277. Min Act: -0.1700
Data Index: 1407729 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.9277. Min Act: -0.1700
Data Index: 7650568 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.8652. Min Act: -0.1700
Data Index: 2039047 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.8652. Min Act: -0.1700
Data Index: 4049917 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.7402. Min Act: -0.1700
Data Index: 5248632 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.8027. Min Act: -0.1700
Data Index: 5071950 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.8027. Min Act: -0.1700
Data Index: 1427020 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6777. Min Range: -9.6777
Max Act: 8.8027. Min Act: -0.1700
Data Index: 7439525 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19