Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.3806. Min Act: -0.1700
Data Index: 8252167 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.2556. Min Act: -0.1700
Data Index: 5317216 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.2244. Min Act: -0.1700
Data Index: 5670740 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.2244. Min Act: -0.1700
Data Index: 1431235 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.1619. Min Act: -0.1700
Data Index: 7224891 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.1306. Min Act: -0.1700
Data Index: 8759016 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0994. Min Act: -0.1700
Data Index: 2770182 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0994. Min Act: -0.1700
Data Index: 6346111 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0994. Min Act: -0.1700
Data Index: 7991494 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0681. Min Act: -0.1700
Data Index: 698860 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0681. Min Act: -0.1700
Data Index: 5954375 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0681. Min Act: -0.1700
Data Index: 3674636 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0369. Min Act: -0.1700
Data Index: 8672333 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0681. Min Act: -0.1700
Data Index: 140643 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0056. Min Act: -0.1700
Data Index: 3704138 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0056. Min Act: -0.1700
Data Index: 2082484 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0056. Min Act: -0.1700
Data Index: 4091613 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0056. Min Act: -0.1700
Data Index: 3138900 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6951200 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3806. Min Range: -5.3806
Max Act: 5.0056. Min Act: -0.1700
Data Index: 7297541 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19