Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 5463629 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 6217502 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 1907514 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9256. Min Act: -0.1700
Data Index: 2099908 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9256. Min Act: -0.1700
Data Index: 8354225 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9256. Min Act: -0.1700
Data Index: 6179543 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8944. Min Act: -0.1700
Data Index: 5074639 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8944. Min Act: -0.1700
Data Index: 1905521 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8944. Min Act: -0.1700
Data Index: 3293175 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8944. Min Act: -0.1700
Data Index: 4062751 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 3330049 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 135929 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 3394315 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 3984072 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 77272 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 4062471 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8319. Min Act: -0.1700
Data Index: 8201238 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8319. Min Act: -0.1700
Data Index: 4674683 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8319. Min Act: -0.1700
Data Index: 5654551 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8631. Min Act: -0.1700
Data Index: 371088 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19