Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4897 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.5150. Min Act: -0.1700
Data Index: 2834948 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.5150. Min Act: -0.1700
Data Index: 2648871 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.5150. Min Act: -0.1700
Data Index: 976520 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4837. Min Act: -0.1700
Data Index: 8498739 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4837. Min Act: -0.1700
Data Index: 861283 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4837. Min Act: -0.1700
Data Index: 3978256 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4525. Min Act: -0.1700
Data Index: 3763477 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4525. Min Act: -0.1700
Data Index: 2067382 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4525. Min Act: -0.1700
Data Index: 7883599 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4525. Min Act: -0.1700
Data Index: 1408396 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4525. Min Act: -0.1700
Data Index: 4785781 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4212. Min Act: -0.1700
Data Index: 6739097 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4212. Min Act: -0.1700
Data Index: 8366162 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4212. Min Act: -0.1700
Data Index: 5131867 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4212. Min Act: -0.1700
Data Index: 4524071 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.4212. Min Act: -0.1700
Data Index: 4896573 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.3587. Min Act: -0.1700
Data Index: 5834156 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.3274. Min Act: -0.1700
Data Index: 984629 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.3274. Min Act: -0.1700
Data Index: 4316946 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5150. Min Range: -4.5150
Max Act: 4.2962. Min Act: -0.1700
Data Index: 6688173 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19