Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0864. Min Range: -8.0864
Max Act: 8.0864. Min Act: -0.1700
Data Index: 8729904 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.7114. Min Act: -0.1700
Data Index: 1966409 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.5864. Min Act: -0.1700
Data Index: 6741334 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.5864. Min Act: -0.1700
Data Index: 5680563 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.5239. Min Act: -0.1700
Data Index: 7742962 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.4614. Min Act: -0.1700
Data Index: 8613690 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.4614. Min Act: -0.1700
Data Index: 4297920 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.3989. Min Act: -0.1700
Data Index: 8479133 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.3989. Min Act: -0.1700
Data Index: 6777184 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.2739. Min Act: -0.1700
Data Index: 987028 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.3364. Min Act: -0.1700
Data Index: 5555437 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.2426. Min Act: -0.1700
Data Index: 4464402 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.2739. Min Act: -0.1700
Data Index: 5723329 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.2739. Min Act: -0.1700
Data Index: 696429 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.2426. Min Act: -0.1700
Data Index: 8429819 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.2426. Min Act: -0.1700
Data Index: 1287366 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.1801. Min Act: -0.1700
Data Index: 8347986 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.1176. Min Act: -0.1700
Data Index: 5849594 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.1176. Min Act: -0.1700
Data Index: 4191633 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0864. Min Range: -8.0864
Max Act: 7.0864. Min Act: -0.1700
Data Index: 6651812 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19