Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0235. Min Range: -8.0235
Max Act: 8.0235. Min Act: -0.1700
Data Index: 1404452 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.8047. Min Act: -0.1700
Data Index: 7429276 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.7422. Min Act: -0.1700
Data Index: 2191107 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.4922. Min Act: -0.1700
Data Index: 4892204 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.4297. Min Act: -0.1700
Data Index: 4051369 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.3672. Min Act: -0.1700
Data Index: 8386102 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.3985. Min Act: -0.1700
Data Index: 6729030 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.3985. Min Act: -0.1700
Data Index: 5820921 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.3360. Min Act: -0.1700
Data Index: 856179 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.2735. Min Act: -0.1700
Data Index: 3829763 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.2422. Min Act: -0.1700
Data Index: 3076415 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.2422. Min Act: -0.1700
Data Index: 3182491 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.2422. Min Act: -0.1700
Data Index: 7360091 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.2110. Min Act: -0.1700
Data Index: 1476557 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.2110. Min Act: -0.1700
Data Index: 6872905 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.1797. Min Act: -0.1700
Data Index: 7800601 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.2110. Min Act: -0.1700
Data Index: 5778926 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.1485. Min Act: -0.1700
Data Index: 945673 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.1485. Min Act: -0.1700
Data Index: 2546241 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0235. Min Range: -8.0235
Max Act: 7.1485. Min Act: -0.1700
Data Index: 6468882 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19