Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6256 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.7020. Min Act: -0.1700
Data Index: 8086066 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.7020. Min Act: -0.1700
Data Index: 7937970 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.5770. Min Act: -0.1700
Data Index: 1807794 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.5770. Min Act: -0.1700
Data Index: 5562247 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.3270. Min Act: -0.1700
Data Index: 4893162 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.3270. Min Act: -0.1700
Data Index: 3821494 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.3270. Min Act: -0.1700
Data Index: 3446470 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.2645. Min Act: -0.1700
Data Index: 2993056 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.2645. Min Act: -0.1700
Data Index: 1256892 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.2645. Min Act: -0.1700
Data Index: 5417882 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.2020. Min Act: -0.1700
Data Index: 811397 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.1395. Min Act: -0.1700
Data Index: 5933404 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.1395. Min Act: -0.1700
Data Index: 1372301 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.0770. Min Act: -0.1700
Data Index: 3616280 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.0770. Min Act: -0.1700
Data Index: 8648717 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.0770. Min Act: -0.1700
Data Index: 5437433 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.0770. Min Act: -0.1700
Data Index: 3579686 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.0770. Min Act: -0.1700
Data Index: 5427931 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.0145. Min Act: -0.1700
Data Index: 5485821 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.0145. Min Act: -0.1700
Data Index: 7381925 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19