Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.4299. Min Act: -0.1700
Data Index: 6509991 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.3674. Min Act: -0.1700
Data Index: 2176806 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.3362. Min Act: -0.1700
Data Index: 4143801 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.3362. Min Act: -0.1700
Data Index: 7187845 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.3049. Min Act: -0.1700
Data Index: 5262738 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.2424. Min Act: -0.1700
Data Index: 4056037 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.2424. Min Act: -0.1700
Data Index: 2562807 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.2112. Min Act: -0.1700
Data Index: 6799524 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.2112. Min Act: -0.1700
Data Index: 3104374 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.1487. Min Act: -0.1700
Data Index: 6877949 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.1487. Min Act: -0.1700
Data Index: 6676074 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.1174. Min Act: -0.1700
Data Index: 745558 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.0862. Min Act: -0.1700
Data Index: 8794700 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.1174. Min Act: -0.1700
Data Index: 2068139 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.0862. Min Act: -0.1700
Data Index: 8253856 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.0862. Min Act: -0.1700
Data Index: 8325293 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.0862. Min Act: -0.1700
Data Index: 6179858 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.0862. Min Act: -0.1700
Data Index: 3047953 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.0862. Min Act: -0.1700
Data Index: 5545692 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4299. Min Range: -5.4299
Max Act: 5.0549. Min Act: -0.1700
Data Index: 5135715 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19