Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3131 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.4293. Min Act: -0.1700
Data Index: 6927741 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3980. Min Act: -0.1700
Data Index: 3956694 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3980. Min Act: -0.1700
Data Index: 2117735 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3980. Min Act: -0.1700
Data Index: 2420946 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3668. Min Act: -0.1700
Data Index: 3733266 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3668. Min Act: -0.1700
Data Index: 6479086 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3355. Min Act: -0.1700
Data Index: 6064110 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3355. Min Act: -0.1700
Data Index: 4490499 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3355. Min Act: -0.1700
Data Index: 7075204 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3043. Min Act: -0.1700
Data Index: 3209679 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.3043. Min Act: -0.1700
Data Index: 3863515 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2730. Min Act: -0.1700
Data Index: 8399140 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 563975 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2105. Min Act: -0.1700
Data Index: 3757043 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 1815740 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 3994884 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 7408736 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 7664415 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 6103919 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4293. Min Range: -6.4293
Max Act: 6.2418. Min Act: -0.1700
Data Index: 1612870 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19