Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.4100. Min Act: -0.1700
Data Index: 5380817 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.4100. Min Act: -0.1700
Data Index: 1667246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.4100. Min Act: -0.1700
Data Index: 1162972 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 620960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 8061533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.4100. Min Act: -0.1700
Data Index: 7876662 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.4100. Min Act: -0.1700
Data Index: 3203358 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 7795281 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 7746916 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 4854021 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 1785738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 1107153 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3788. Min Act: -0.1700
Data Index: 2215527 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 715520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 915181 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 4444074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 7544436 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 633213 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 6414911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 5964276 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19