Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5640 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0491. Min Range: -6.0491
Max Act: 6.0491. Min Act: -0.1700
Data Index: 1418014 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.9554. Min Act: -0.1700
Data Index: 3358489 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.8304. Min Act: -0.1700
Data Index: 7359771 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.7366. Min Act: -0.1700
Data Index: 8076488 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.6429. Min Act: -0.1700
Data Index: 4163234 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.5804. Min Act: -0.1700
Data Index: 2495770 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.5804. Min Act: -0.1700
Data Index: 2326808 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4866. Min Act: -0.1700
Data Index: 2189970 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.5179. Min Act: -0.1700
Data Index: 3229970 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4866. Min Act: -0.1700
Data Index: 989186 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4866. Min Act: -0.1700
Data Index: 5395674 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4554. Min Act: -0.1700
Data Index: 5125263 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4866. Min Act: -0.1700
Data Index: 8060542 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4241. Min Act: -0.1700
Data Index: 1705852 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4241. Min Act: -0.1700
Data Index: 4255368 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4241. Min Act: -0.1700
Data Index: 579794 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4241. Min Act: -0.1700
Data Index: 6452407 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4241. Min Act: -0.1700
Data Index: 5550899 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4241. Min Act: -0.1700
Data Index: 8591138 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0491. Min Range: -6.0491
Max Act: 5.4241. Min Act: -0.1700
Data Index: 7363245 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19