Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3401 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0476. Min Range: -4.0476
Max Act: 4.0476. Min Act: -0.1700
Data Index: 6683891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0476. Min Range: -4.0476
Max Act: 4.0476. Min Act: -0.1700
Data Index: 4733403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0476. Min Range: -4.0476
Max Act: 4.0476. Min Act: -0.1700
Data Index: 2867695 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0476. Min Range: -4.0476
Max Act: 4.0476. Min Act: -0.1700
Data Index: 2040284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.8444. Min Act: -0.1700
Data Index: 1719702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.8444. Min Act: -0.1700
Data Index: 7169182 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.8444. Min Act: -0.1700
Data Index: 4427213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.8444. Min Act: -0.1700
Data Index: 2821492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.7818. Min Act: -0.1700
Data Index: 6230436 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.7662. Min Act: -0.1700
Data Index: 187274 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.7193. Min Act: -0.1700
Data Index: 7003770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.6411. Min Act: -0.1700
Data Index: 4668366 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.6411. Min Act: -0.1700
Data Index: 6833929 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.6098. Min Act: -0.1700
Data Index: 3343550 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.5941. Min Act: -0.1700
Data Index: 3258054 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.5785. Min Act: -0.1700
Data Index: 4841876 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.5628. Min Act: -0.1700
Data Index: 2705233 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.5472. Min Act: -0.1700
Data Index: 6402092 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.5472. Min Act: -0.1700
Data Index: 5906533 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0476. Min Range: -4.0476
Max Act: 3.5472. Min Act: -0.1700
Data Index: 6331192 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19