Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5041889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.5354. Min Act: -0.1700
Data Index: 8308588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4729. Min Act: -0.1700
Data Index: 8411389 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4417. Min Act: -0.1700
Data Index: 2763395 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4417. Min Act: -0.1700
Data Index: 1407209 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4104. Min Act: -0.1700
Data Index: 4515211 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4104. Min Act: -0.1700
Data Index: 5041188 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4104. Min Act: -0.1700
Data Index: 3186785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4104. Min Act: -0.1700
Data Index: 2897606 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.4104. Min Act: -0.1700
Data Index: 5997017 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 7002114 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 53662 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 896361 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 1486962 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 191334 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 3908156 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 8305173 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 5928014 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3792. Min Act: -0.1700
Data Index: 4338334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5667. Min Range: -5.5667
Max Act: 5.3479. Min Act: -0.1700
Data Index: 3427679 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19