Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3715 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.7677. Min Act: -0.1700
Data Index: 3238968 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.6427. Min Act: -0.1700
Data Index: 8786373 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.5802. Min Act: -0.1700
Data Index: 5790050 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.6115. Min Act: -0.1700
Data Index: 8063481 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4552. Min Act: -0.1700
Data Index: 4895351 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4552. Min Act: -0.1700
Data Index: 3171203 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4865. Min Act: -0.1700
Data Index: 565492 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4865. Min Act: -0.1700
Data Index: 7034796 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4865. Min Act: -0.1700
Data Index: 6797 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.5177. Min Act: -0.1700
Data Index: 730321 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4552. Min Act: -0.1700
Data Index: 7457719 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4552. Min Act: -0.1700
Data Index: 4140179 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4240. Min Act: -0.1700
Data Index: 6167714 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4240. Min Act: -0.1700
Data Index: 6782957 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4240. Min Act: -0.1700
Data Index: 1796358 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.4240. Min Act: -0.1700
Data Index: 3298874 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.3927. Min Act: -0.1700
Data Index: 6792079 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.3927. Min Act: -0.1700
Data Index: 1796361 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.3927. Min Act: -0.1700
Data Index: 219951 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7677. Min Range: -7.7677
Max Act: 7.3927. Min Act: -0.1700
Data Index: 2446565 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19