Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 952 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.8486. Min Act: -0.1700
Data Index: 2369383 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.7236. Min Act: -0.1700
Data Index: 5295321 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.6299. Min Act: -0.1700
Data Index: 8256044 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.5361. Min Act: -0.1700
Data Index: 4304073 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.4736. Min Act: -0.1700
Data Index: 8778220 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.5049. Min Act: -0.1700
Data Index: 2366210 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.4111. Min Act: -0.1700
Data Index: 8706968 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.4111. Min Act: -0.1700
Data Index: 2868342 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.3486. Min Act: -0.1700
Data Index: 8372249 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.3486. Min Act: -0.1700
Data Index: 8384253 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.3174. Min Act: -0.1693
Data Index: 655287 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.3174. Min Act: -0.1700
Data Index: 5356209 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2861. Min Act: -0.1699
Data Index: 5003194 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2861. Min Act: -0.1700
Data Index: 7139834 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2861. Min Act: -0.1700
Data Index: 6787555 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2549. Min Act: -0.1700
Data Index: 6746282 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2549. Min Act: -0.1699
Data Index: 697335 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2236. Min Act: -0.1700
Data Index: 1379426 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2236. Min Act: -0.1700
Data Index: 2793194 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8486. Min Range: -6.8486
Max Act: 6.2236. Min Act: -0.1699
Data Index: 7139833 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19