Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 249 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5052618 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.6380. Min Act: -0.1700
Data Index: 5669465 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.6380. Min Act: -0.1700
Data Index: 2170441 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.6068. Min Act: -0.1700
Data Index: 2612842 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.6068. Min Act: -0.1700
Data Index: 8656543 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.6068. Min Act: -0.1700
Data Index: 1741358 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5755. Min Act: -0.1700
Data Index: 122623 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.6068. Min Act: -0.1700
Data Index: 4981212 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5443. Min Act: -0.1700
Data Index: 5789383 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5443. Min Act: -0.1700
Data Index: 1479513 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5443. Min Act: -0.1700
Data Index: 1978967 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 3023818 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 4363736 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 7388353 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 3914164 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.4818. Min Act: -0.1700
Data Index: 5778111 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.4818. Min Act: -0.1700
Data Index: 819569 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 558233 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.4818. Min Act: -0.1700
Data Index: 2881047 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7318. Min Range: -6.7318
Max Act: 6.4818. Min Act: -0.1700
Data Index: 1702379 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19