Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.5918. Min Act: -0.1700
Data Index: 6328109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.5605. Min Act: -0.1700
Data Index: 4792809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.5918. Min Act: -0.1700
Data Index: 620555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4979. Min Act: -0.1700
Data Index: 4866519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4979. Min Act: -0.1700
Data Index: 6377919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4666. Min Act: -0.1700
Data Index: 3658950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4666. Min Act: -0.1700
Data Index: 1215191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4352. Min Act: -0.1700
Data Index: 3421743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4352. Min Act: -0.1700
Data Index: 7996989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4352. Min Act: -0.1700
Data Index: 8255290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4352. Min Act: -0.1700
Data Index: 8707771 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4039. Min Act: -0.1700
Data Index: 2741350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.4039. Min Act: -0.1700
Data Index: 2205387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.3725. Min Act: -0.1700
Data Index: 8400112 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.3725. Min Act: -0.1700
Data Index: 6379620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.3725. Min Act: -0.1700
Data Index: 53245 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.3725. Min Act: -0.1700
Data Index: 2581782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.3725. Min Act: -0.1700
Data Index: 8392621 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.3725. Min Act: -0.1700
Data Index: 7536361 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5918. Min Range: -3.5918
Max Act: 3.3411. Min Act: -0.1700
Data Index: 6942357 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19