Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4597 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.4700. Min Act: -0.1700
Data Index: 127015 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.3395. Min Act: -0.1700
Data Index: 5923473 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.3395. Min Act: -0.1700
Data Index: 1945710 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.3231. Min Act: -0.1700
Data Index: 1073407 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2902. Min Act: -0.1700
Data Index: 476615 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2737. Min Act: -0.1700
Data Index: 272174 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2572. Min Act: -0.1700
Data Index: 5037704 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2572. Min Act: -0.1700
Data Index: 5968817 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2407. Min Act: -0.1700
Data Index: 3663962 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2407. Min Act: -0.1700
Data Index: 4590533 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2407. Min Act: -0.1700
Data Index: 2270585 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2407. Min Act: -0.1700
Data Index: 2086823 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2407. Min Act: -0.1700
Data Index: 7347151 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2407. Min Act: -0.1700
Data Index: 2721317 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2407. Min Act: -0.1700
Data Index: 2879570 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2241. Min Act: -0.1700
Data Index: 2721316 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2241. Min Act: -0.1700
Data Index: 7979731 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2076. Min Act: -0.1700
Data Index: 2369170 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.2076. Min Act: -0.1700
Data Index: 5194503 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4700. Min Range: -2.4700
Max Act: 2.1910. Min Act: -0.1700
Data Index: 3528402 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19