Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4012 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.6866. Min Act: -0.1700
Data Index: 740241 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.7178. Min Act: -0.1700
Data Index: 8360772 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.6553. Min Act: -0.1700
Data Index: 1234310 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.6241. Min Act: -0.1700
Data Index: 2743051 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.5928. Min Act: -0.1700
Data Index: 7975358 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.5928. Min Act: -0.1700
Data Index: 6793703 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.5928. Min Act: -0.1700
Data Index: 654171 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.5928. Min Act: -0.1700
Data Index: 1650276 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.4991. Min Act: -0.1700
Data Index: 5571095 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.4991. Min Act: -0.1700
Data Index: 4318398 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.4366. Min Act: -0.1700
Data Index: 592207 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.4053. Min Act: -0.1700
Data Index: 5802090 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.3428. Min Act: -0.1700
Data Index: 1177513 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.3741. Min Act: -0.1700
Data Index: 2707410 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.3428. Min Act: -0.1700
Data Index: 2018136 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.3428. Min Act: -0.1700
Data Index: 4300818 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.3428. Min Act: -0.1700
Data Index: 6725650 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.3116. Min Act: -0.1700
Data Index: 5043692 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.2803. Min Act: -0.1700
Data Index: 7559500 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7178. Min Range: -6.7178
Max Act: 6.2803. Min Act: -0.1700
Data Index: 5396550 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19