Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1263 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0998. Min Act: -0.1700
Data Index: 7476214 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.1166. Min Act: -0.1700
Data Index: 7822534 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.1166. Min Act: -0.1700
Data Index: 4524840 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0831. Min Act: -0.1700
Data Index: 6009531 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0831. Min Act: -0.1700
Data Index: 5549218 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0831. Min Act: -0.1700
Data Index: 6825054 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0831. Min Act: -0.1700
Data Index: 4784992 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0663. Min Act: -0.1700
Data Index: 5549221 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0495. Min Act: -0.1700
Data Index: 6888589 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2956341 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0326. Min Act: -0.1700
Data Index: 7476204 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0158. Min Act: -0.1700
Data Index: 5666941 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0158. Min Act: -0.1700
Data Index: 6582140 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0326. Min Act: -0.1700
Data Index: 2956346 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1166. Min Range: -2.1166
Max Act: 1.9989. Min Act: -0.1700
Data Index: 7476211 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1166. Min Range: -2.1166
Max Act: 2.0158. Min Act: -0.1700
Data Index: 714534 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1166. Min Range: -2.1166
Max Act: 1.9820. Min Act: -0.1700
Data Index: 6009532 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1166. Min Range: -2.1166
Max Act: 1.9820. Min Act: -0.1700
Data Index: 7659726 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1166. Min Range: -2.1166
Max Act: 1.9820. Min Act: -0.1700
Data Index: 4512748 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1166. Min Range: -2.1166
Max Act: 1.9820. Min Act: -0.1700
Data Index: 7659725 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19