Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5006. Min Range: -7.5006
Max Act: 7.5006. Min Act: -0.1700
Data Index: 5246221 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5006. Min Range: -7.5006
Max Act: 7.4069. Min Act: -0.1700
Data Index: 4210956 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5006. Min Range: -7.5006
Max Act: 7.1881. Min Act: -0.1700
Data Index: 1778134 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5006. Min Range: -7.5006
Max Act: 7.0319. Min Act: -0.1700
Data Index: 4886272 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.9694. Min Act: -0.1700
Data Index: 8667655 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.9381. Min Act: -0.1700
Data Index: 7371313 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.8444. Min Act: -0.1700
Data Index: 5645591 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.8131. Min Act: -0.1700
Data Index: 4349865 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.7819. Min Act: -0.1700
Data Index: 7498769 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.7506. Min Act: -0.1700
Data Index: 3305900 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.7506. Min Act: -0.1700
Data Index: 3538087 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.7194. Min Act: -0.1700
Data Index: 5447195 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.7194. Min Act: -0.1700
Data Index: 3310957 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.6881. Min Act: -0.1700
Data Index: 1971693 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.6569. Min Act: -0.1700
Data Index: 4232616 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.6569. Min Act: -0.1700
Data Index: 3004750 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.6256. Min Act: -0.1700
Data Index: 7252950 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.5944. Min Act: -0.1700
Data Index: 817610 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.5944. Min Act: -0.1700
Data Index: 3412765 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5006. Min Range: -7.5006
Max Act: 6.5944. Min Act: -0.1700
Data Index: 2469242 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19