Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.1088. Min Act: -0.1700
Data Index: 344470 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0930. Min Act: -0.1700
Data Index: 570193 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0930. Min Act: -0.1700
Data Index: 7647216 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0615. Min Act: -0.1700
Data Index: 4589110 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0299. Min Act: -0.1700
Data Index: 2196727 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0299. Min Act: -0.1700
Data Index: 6113372 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0141. Min Act: -0.1700
Data Index: 8029476 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0141. Min Act: -0.1700
Data Index: 332747 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0141. Min Act: -0.1700
Data Index: 7953121 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0141. Min Act: -0.1700
Data Index: 3652794 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0141. Min Act: -0.1700
Data Index: 7270025 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1088. Min Range: -3.1088
Max Act: 3.0141. Min Act: -0.1700
Data Index: 6624924 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9983. Min Act: -0.1700
Data Index: 1080001 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9983. Min Act: -0.1700
Data Index: 8263719 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9825. Min Act: -0.1700
Data Index: 7420828 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9825. Min Act: -0.1700
Data Index: 7310171 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9825. Min Act: -0.1700
Data Index: 7081619 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9825. Min Act: -0.1700
Data Index: 2667417 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9825. Min Act: -0.1700
Data Index: 86400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1088. Min Range: -3.1088
Max Act: 2.9825. Min Act: -0.1700
Data Index: 5359141 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19