Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.8433. Min Act: -0.1700
Data Index: 731950 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.9058. Min Act: -0.1700
Data Index: 3678016 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.7808. Min Act: -0.1700
Data Index: 1895749 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.7183. Min Act: -0.1700
Data Index: 5814065 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.7183. Min Act: -0.1700
Data Index: 8436636 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.5308. Min Act: -0.1700
Data Index: 1707585 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.5933. Min Act: -0.1700
Data Index: 2741536 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.4058. Min Act: -0.1700
Data Index: 8817689 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.3433. Min Act: -0.1700
Data Index: 4249546 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.3433. Min Act: -0.1700
Data Index: 4559417 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.3433. Min Act: -0.1700
Data Index: 2984299 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.2808. Min Act: -0.1700
Data Index: 1956854 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.2183. Min Act: -0.1700
Data Index: 3522733 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.1558. Min Act: -0.1700
Data Index: 5566356 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.2183. Min Act: -0.1700
Data Index: 5917816 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.2183. Min Act: -0.1700
Data Index: 5533356 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.2183. Min Act: -0.1700
Data Index: 3515083 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.1558. Min Act: -0.1700
Data Index: 5731263 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.1558. Min Act: -0.1700
Data Index: 7707474 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9058. Min Range: -8.9058
Max Act: 8.1558. Min Act: -0.1700
Data Index: 4204506 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19