Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3912 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.6345. Min Act: -0.1700
Data Index: 3368939 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.4783. Min Act: -0.1700
Data Index: 7979595 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.2283. Min Act: -0.1700
Data Index: 516827 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.1970. Min Act: -0.1700
Data Index: 2740476 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.1970. Min Act: -0.1700
Data Index: 2534311 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.1658. Min Act: -0.1700
Data Index: 5959582 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.1345. Min Act: -0.1700
Data Index: 957338 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.1345. Min Act: -0.1700
Data Index: 1397628 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.1033. Min Act: -0.1700
Data Index: 4082990 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.0720. Min Act: -0.1700
Data Index: 8726479 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.0407. Min Act: -0.1700
Data Index: 5254365 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.0095. Min Act: -0.1700
Data Index: 8169558 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.0095. Min Act: -0.1700
Data Index: 262183 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.0095. Min Act: -0.1700
Data Index: 7253607 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6345. Min Range: -4.6345
Max Act: 3.9782. Min Act: -0.1700
Data Index: 8336901 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6345. Min Range: -4.6345
Max Act: 3.9782. Min Act: -0.1700
Data Index: 5265589 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6345. Min Range: -4.6345
Max Act: 3.9782. Min Act: -0.1700
Data Index: 7319859 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.0095. Min Act: -0.1700
Data Index: 4740135 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6345. Min Range: -4.6345
Max Act: 4.0095. Min Act: -0.1700
Data Index: 2005743 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6345. Min Range: -4.6345
Max Act: 3.9782. Min Act: -0.1700
Data Index: 4038669 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19