Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.7565. Min Act: -0.1700
Data Index: 7809460 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6893996 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4440. Min Act: -0.1700
Data Index: 6030140 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4440. Min Act: -0.1700
Data Index: 299940 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4440. Min Act: -0.1700
Data Index: 751040 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4128. Min Act: -0.1700
Data Index: 5220061 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3503. Min Act: -0.1700
Data Index: 574403 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3190. Min Act: -0.1700
Data Index: 4776414 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3190. Min Act: -0.1700
Data Index: 8567143 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3190. Min Act: -0.1700
Data Index: 6313516 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3190. Min Act: -0.1700
Data Index: 675548 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2878. Min Act: -0.1700
Data Index: 4287592 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2878. Min Act: -0.1700
Data Index: 800840 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2878. Min Act: -0.1700
Data Index: 8428424 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3190. Min Act: -0.1700
Data Index: 1151266 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2565. Min Act: -0.1700
Data Index: 3528015 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2565. Min Act: -0.1700
Data Index: 7788496 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2253. Min Act: -0.1700
Data Index: 742117 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2253. Min Act: -0.1700
Data Index: 676349 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.2253. Min Act: -0.1700
Data Index: 7222448 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19