Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5140 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.9005. Min Act: -0.1700
Data Index: 3616320 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8692. Min Act: -0.1700
Data Index: 555693 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8692. Min Act: -0.1700
Data Index: 4291562 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8692. Min Act: -0.1700
Data Index: 1276243 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8692. Min Act: -0.1700
Data Index: 5081818 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8380. Min Act: -0.1700
Data Index: 555694 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8380. Min Act: -0.1700
Data Index: 5344042 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8380. Min Act: -0.1700
Data Index: 6320301 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8380. Min Act: -0.1700
Data Index: 6320302 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8067. Min Act: -0.1700
Data Index: 7765338 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.8067. Min Act: -0.1700
Data Index: 3152669 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7755. Min Act: -0.1700
Data Index: 8305910 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7755. Min Act: -0.1700
Data Index: 757409 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7755. Min Act: -0.1700
Data Index: 3032959 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7755. Min Act: -0.1700
Data Index: 672661 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7755. Min Act: -0.1700
Data Index: 5398696 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5650990 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7442. Min Act: -0.1700
Data Index: 3394713 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5187158 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9005. Min Range: -5.9005
Max Act: 5.7755. Min Act: -0.1700
Data Index: 1630339 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19