Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6147 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.2873. Min Act: -0.1700
Data Index: 8662149 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.2401. Min Act: -0.1700
Data Index: 5832531 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1772. Min Act: -0.1700
Data Index: 1304490 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1300. Min Act: -0.1700
Data Index: 2694523 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1615. Min Act: -0.1700
Data Index: 5832532 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1300. Min Act: -0.1700
Data Index: 8318668 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1300. Min Act: -0.1700
Data Index: 1370422 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1300. Min Act: -0.1700
Data Index: 987945 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1300. Min Act: -0.1700
Data Index: 6487750 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0827. Min Act: -0.1700
Data Index: 2794364 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0827. Min Act: -0.1700
Data Index: 2511064 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0512. Min Act: -0.1700
Data Index: 583657 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0354. Min Act: -0.1700
Data Index: 5832527 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0354. Min Act: -0.1700
Data Index: 2642023 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0196. Min Act: -0.1700
Data Index: 7076465 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0038. Min Act: -0.1700
Data Index: 4631906 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0196. Min Act: -0.1700
Data Index: 3263019 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0196. Min Act: -0.1700
Data Index: 3263012 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2873. Min Range: -3.2873
Max Act: 2.9880. Min Act: -0.1700
Data Index: 8211004 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0196. Min Act: -0.1700
Data Index: 4518286 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19