Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5893 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.5121. Min Act: -0.1700
Data Index: 6915638 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.4496. Min Act: -0.1700
Data Index: 609721 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.4496. Min Act: -0.1700
Data Index: 1798904 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.4496. Min Act: -0.1700
Data Index: 3752898 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.4184. Min Act: -0.1700
Data Index: 4837548 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.4184. Min Act: -0.1700
Data Index: 2539234 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.4184. Min Act: -0.1700
Data Index: 4872138 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3871. Min Act: -0.1700
Data Index: 4125914 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3871. Min Act: -0.1700
Data Index: 6041773 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3559. Min Act: -0.1700
Data Index: 2169807 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3559. Min Act: -0.1700
Data Index: 3039606 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.2934. Min Act: -0.1700
Data Index: 5040906 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.2934. Min Act: -0.1700
Data Index: 7117927 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3246. Min Act: -0.1700
Data Index: 125152 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.2934. Min Act: -0.1700
Data Index: 8463696 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3246. Min Act: -0.1700
Data Index: 4366963 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3559. Min Act: -0.1700
Data Index: 166024 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3246. Min Act: -0.1700
Data Index: 2765554 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3246. Min Act: -0.1700
Data Index: 4053515 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5121. Min Range: -5.5121
Max Act: 5.3246. Min Act: -0.1700
Data Index: 4233134 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19