Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.9285. Min Act: -0.1700
Data Index: 7330376 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.7410. Min Act: -0.1700
Data Index: 2590059 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.6160. Min Act: -0.1700
Data Index: 2165153 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.4285. Min Act: -0.1700
Data Index: 7895381 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.4285. Min Act: -0.1700
Data Index: 5930117 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3660. Min Act: -0.1700
Data Index: 4277258 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3035. Min Act: -0.1700
Data Index: 5351864 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3660. Min Act: -0.1700
Data Index: 4417785 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3660. Min Act: -0.1700
Data Index: 7278849 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3035. Min Act: -0.1700
Data Index: 4826902 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3035. Min Act: -0.1700
Data Index: 8702427 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3035. Min Act: -0.1700
Data Index: 5182229 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3035. Min Act: -0.1700
Data Index: 2418439 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.2410. Min Act: -0.1700
Data Index: 5911062 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.2410. Min Act: -0.1700
Data Index: 177175 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.3035. Min Act: -0.1700
Data Index: 2389937 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.2410. Min Act: -0.1700
Data Index: 5386965 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.2410. Min Act: -0.1700
Data Index: 1257443 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.2410. Min Act: -0.1700
Data Index: 2314930 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9285. Min Range: -8.9285
Max Act: 8.2410. Min Act: -0.1700
Data Index: 199308 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19