Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.6334. Min Act: -0.1700
Data Index: 3118149 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.5084. Min Act: -0.1700
Data Index: 5847987 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.5084. Min Act: -0.1700
Data Index: 4253605 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.4459. Min Act: -0.1700
Data Index: 4598920 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.4459. Min Act: -0.1700
Data Index: 6584540 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.4459. Min Act: -0.1700
Data Index: 3797981 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.5084. Min Act: -0.1700
Data Index: 1122002 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3834. Min Act: -0.1700
Data Index: 7574299 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3834. Min Act: -0.1700
Data Index: 2995835 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3834. Min Act: -0.1700
Data Index: 6584541 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3834. Min Act: -0.1700
Data Index: 8480859 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3209. Min Act: -0.1700
Data Index: 1294932 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3834. Min Act: -0.1700
Data Index: 2924387 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3209. Min Act: -0.1700
Data Index: 7532156 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3209. Min Act: -0.1700
Data Index: 4188260 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3209. Min Act: -0.1700
Data Index: 1419556 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3209. Min Act: -0.1700
Data Index: 8544165 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3209. Min Act: -0.1700
Data Index: 1122009 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.3209. Min Act: -0.1700
Data Index: 6599192 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6334. Min Range: -8.6334
Max Act: 8.2584. Min Act: -0.1700
Data Index: 2775298 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19