Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2958. Min Act: -0.1700
Data Index: 2607589 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2801. Min Act: -0.1700
Data Index: 8771449 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2801. Min Act: -0.1700
Data Index: 6677806 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2486. Min Act: -0.1700
Data Index: 2596101 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2486. Min Act: -0.1700
Data Index: 4704012 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2486. Min Act: -0.1700
Data Index: 2084061 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2486. Min Act: -0.1700
Data Index: 2867031 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2172. Min Act: -0.1700
Data Index: 8735042 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2329. Min Act: -0.1700
Data Index: 671523 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2329. Min Act: -0.1700
Data Index: 4078587 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2172. Min Act: -0.1700
Data Index: 1943796 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2329. Min Act: -0.1700
Data Index: 1683188 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.2015. Min Act: -0.1700
Data Index: 4119383 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.1858. Min Act: -0.1700
Data Index: 1019938 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.1700. Min Act: -0.1700
Data Index: 5935856 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.1858. Min Act: -0.1700
Data Index: 8387881 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.1700. Min Act: -0.1700
Data Index: 368385 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.1700. Min Act: -0.1700
Data Index: 4758882 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.1385. Min Act: -0.1700
Data Index: 4440266 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2958. Min Range: -3.2958
Max Act: 3.1543. Min Act: -0.1700
Data Index: 4482335 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19