Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.6278. Min Act: -0.1700
Data Index: 4483320 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.4090. Min Act: -0.1700
Data Index: 8418460 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.3153. Min Act: -0.1700
Data Index: 203881 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.1278. Min Act: -0.1700
Data Index: 7977960 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6278. Min Range: -6.6278
Max Act: 6.0965. Min Act: -0.1700
Data Index: 6029533 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.9715. Min Act: -0.1700
Data Index: 5991211 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.9090. Min Act: -0.1700
Data Index: 803854 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.9090. Min Act: -0.1700
Data Index: 6148595 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8778. Min Act: -0.1700
Data Index: 216241 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8778. Min Act: -0.1700
Data Index: 1731702 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8778. Min Act: -0.1700
Data Index: 635742 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8465. Min Act: -0.1700
Data Index: 2796025 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8778. Min Act: -0.1700
Data Index: 4104022 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8153. Min Act: -0.1700
Data Index: 467058 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8153. Min Act: -0.1700
Data Index: 6029528 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.8465. Min Act: -0.1700
Data Index: 6547159 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8790893 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.7840. Min Act: -0.1700
Data Index: 5105185 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.7840. Min Act: -0.1700
Data Index: 4257152 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6278. Min Range: -6.6278
Max Act: 5.7840. Min Act: -0.1700
Data Index: 484221 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19