Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.5364. Min Act: -0.1700
Data Index: 5555997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.5051. Min Act: -0.1700
Data Index: 7533640 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4894. Min Act: -0.1700
Data Index: 2057548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4894. Min Act: -0.1700
Data Index: 5445327 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4268. Min Act: -0.1700
Data Index: 6173175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4268. Min Act: -0.1700
Data Index: 2643539 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4111. Min Act: -0.1700
Data Index: 561582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4111. Min Act: -0.1700
Data Index: 5365102 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4111. Min Act: -0.1700
Data Index: 7765688 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4111. Min Act: -0.1700
Data Index: 5602455 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.4111. Min Act: -0.1700
Data Index: 3312135 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3797. Min Act: -0.1700
Data Index: 5865320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3954. Min Act: -0.1700
Data Index: 5861984 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3954. Min Act: -0.1700
Data Index: 3652302 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3954. Min Act: -0.1700
Data Index: 3871883 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3954. Min Act: -0.1700
Data Index: 4939831 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3797. Min Act: -0.1700
Data Index: 3192146 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3797. Min Act: -0.1700
Data Index: 2336313 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3797. Min Act: -0.1700
Data Index: 3150273 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5364. Min Range: -3.5364
Max Act: 3.3797. Min Act: -0.1700
Data Index: 3523745 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19