Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.7388. Min Act: -0.1700
Data Index: 5304182 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.6763. Min Act: -0.1700
Data Index: 4155075 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.6450. Min Act: -0.1700
Data Index: 8677020 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.6138. Min Act: -0.1700
Data Index: 4576116 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.6138. Min Act: -0.1700
Data Index: 4350363 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.5825. Min Act: -0.1700
Data Index: 6244838 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.5200. Min Act: -0.1700
Data Index: 3885059 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.5200. Min Act: -0.1700
Data Index: 6042658 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.4263. Min Act: -0.1700
Data Index: 8195140 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3950. Min Act: -0.1700
Data Index: 782536 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.4575. Min Act: -0.1700
Data Index: 7036265 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3950. Min Act: -0.1700
Data Index: 2439463 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3950. Min Act: -0.1700
Data Index: 3590503 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3950. Min Act: -0.1700
Data Index: 485002 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3638. Min Act: -0.1700
Data Index: 6243261 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3638. Min Act: -0.1700
Data Index: 1933367 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3638. Min Act: -0.1700
Data Index: 3081826 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3638. Min Act: -0.1700
Data Index: 664124 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3325. Min Act: -0.1700
Data Index: 3444690 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7388. Min Range: -5.7388
Max Act: 5.3325. Min Act: -0.1700
Data Index: 2737056 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19