Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.4858. Min Act: -0.1700
Data Index: 6570203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.5171. Min Act: -0.1700
Data Index: 452495 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.4546. Min Act: -0.1700
Data Index: 4884043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.3921. Min Act: -0.1700
Data Index: 6753746 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.3921. Min Act: -0.1700
Data Index: 4488792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.3608. Min Act: -0.1700
Data Index: 4341622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.3608. Min Act: -0.1700
Data Index: 8477692 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.3296. Min Act: -0.1700
Data Index: 5315056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2983. Min Act: -0.1700
Data Index: 7578703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.3296. Min Act: -0.1700
Data Index: 4998180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2983. Min Act: -0.1700
Data Index: 4498190 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2983. Min Act: -0.1700
Data Index: 3393874 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2983. Min Act: -0.1700
Data Index: 7234679 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2358. Min Act: -0.1700
Data Index: 5643436 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2671. Min Act: -0.1700
Data Index: 1168272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2358. Min Act: -0.1700
Data Index: 4298376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2671. Min Act: -0.1700
Data Index: 4344124 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2358. Min Act: -0.1700
Data Index: 7283826 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2358. Min Act: -0.1700
Data Index: 4344114 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5171. Min Range: -4.5171
Max Act: 4.2358. Min Act: -0.1700
Data Index: 5438595 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19