Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.7362. Min Act: -0.1700
Data Index: 3624761 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.4237. Min Act: -0.1700
Data Index: 4712236 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.3612. Min Act: -0.1700
Data Index: 246277 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.3612. Min Act: -0.1700
Data Index: 2819527 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.2362. Min Act: -0.1700
Data Index: 4627838 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.2362. Min Act: -0.1700
Data Index: 3520136 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.2362. Min Act: -0.1700
Data Index: 7731727 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.2362. Min Act: -0.1700
Data Index: 7044462 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1737. Min Act: -0.1700
Data Index: 6244931 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1112. Min Act: -0.1700
Data Index: 8590217 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1737. Min Act: -0.1700
Data Index: 4152479 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1112. Min Act: -0.1700
Data Index: 5904217 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1112. Min Act: -0.1700
Data Index: 658647 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1112. Min Act: -0.1700
Data Index: 292527 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1112. Min Act: -0.1700
Data Index: 8052964 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.0487. Min Act: -0.1700
Data Index: 5980278 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.0487. Min Act: -0.1700
Data Index: 1955046 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.1112. Min Act: -0.1700
Data Index: 5870275 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7362. Min Range: -8.7362
Max Act: 8.0487. Min Act: -0.1700
Data Index: 1332456 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7362. Min Range: -8.7362
Max Act: 7.9862. Min Act: -0.1700
Data Index: 5388029 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19