Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0058. Min Range: -7.0058
Max Act: 7.0058. Min Act: -0.1700
Data Index: 5655368 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.9745. Min Act: -0.1700
Data Index: 5624218 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.5058. Min Act: -0.1700
Data Index: 4720463 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.2558. Min Act: -0.1700
Data Index: 8636180 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.2245. Min Act: -0.1700
Data Index: 3911426 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.0683. Min Act: -0.1700
Data Index: 404014 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.0370. Min Act: -0.1700
Data Index: 3141800 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.0058. Min Act: -0.1700
Data Index: 3368018 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.0058. Min Act: -0.1700
Data Index: 7610456 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.9745. Min Act: -0.1700
Data Index: 6592937 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0058. Min Range: -7.0058
Max Act: 6.0058. Min Act: -0.1700
Data Index: 1610303 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.8495. Min Act: -0.1700
Data Index: 1704677 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.8808. Min Act: -0.1700
Data Index: 4929486 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.7870. Min Act: -0.1700
Data Index: 4294631 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.8183. Min Act: -0.1700
Data Index: 8632834 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.8495. Min Act: -0.1700
Data Index: 2094794 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.8183. Min Act: -0.1700
Data Index: 4282800 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.7558. Min Act: -0.1700
Data Index: 3115092 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.7870. Min Act: -0.1700
Data Index: 6724654 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0058. Min Range: -7.0058
Max Act: 5.7558. Min Act: -0.1700
Data Index: 7500522 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19