Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.8643. Min Act: -0.1700
Data Index: 735609 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.7393. Min Act: -0.1700
Data Index: 6162048 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4893. Min Act: -0.1700
Data Index: 4123949 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.5518. Min Act: -0.1700
Data Index: 2327542 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4893. Min Act: -0.1700
Data Index: 3963619 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4893. Min Act: -0.1700
Data Index: 312444 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4893. Min Act: -0.1700
Data Index: 3360329 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4268. Min Act: -0.1700
Data Index: 8079317 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4268. Min Act: -0.1700
Data Index: 7498185 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4268. Min Act: -0.1700
Data Index: 2633210 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4893. Min Act: -0.1700
Data Index: 3056488 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 5677616 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3018. Min Act: -0.1700
Data Index: 7868961 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 6349098 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 6349092 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 1276662 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.4268. Min Act: -0.1700
Data Index: 4775242 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 2468513 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 1276661 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8643. Min Range: -8.8643
Max Act: 8.3643. Min Act: -0.1700
Data Index: 3430382 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19