Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2178 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.7908. Min Act: -0.1700
Data Index: 5085213 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.6970. Min Act: -0.1700
Data Index: 8180784 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.6345. Min Act: -0.1700
Data Index: 2287160 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.5408. Min Act: -0.1700
Data Index: 4356971 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.4158. Min Act: -0.1700
Data Index: 5320139 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.3220. Min Act: -0.1700
Data Index: 6849807 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.3220. Min Act: -0.1700
Data Index: 5272100 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.3220. Min Act: -0.1700
Data Index: 658133 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.2595. Min Act: -0.1700
Data Index: 3585343 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.2595. Min Act: -0.1700
Data Index: 688326 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.2283. Min Act: -0.1700
Data Index: 7220504 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.2595. Min Act: -0.1700
Data Index: 6837903 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.2283. Min Act: -0.1700
Data Index: 236832 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.1970. Min Act: -0.1700
Data Index: 7997814 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 1272636 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 6048587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 5679420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.1345. Min Act: -0.1700
Data Index: 599682 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.1970. Min Act: -0.1700
Data Index: 1764582 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7908. Min Range: -5.7908
Max Act: 5.1658. Min Act: -0.1700
Data Index: 5144855 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19