Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 14001 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 584051 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 532123 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 506922 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 466444 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 461945 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 571015 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 392624 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 56850 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 32306 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 206433 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 120122 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 88092 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 175339 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 156723 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 12287 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 326283 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 315591 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 307792 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3682. Min Range: -3.3682
Max Act: 3.3682. Min Act: -0.1700
Data Index: 222209 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19