Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1254 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0167. Min Range: -7.0167
Max Act: 7.0167. Min Act: -0.1700
Data Index: 5988171 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.9230. Min Act: -0.1700
Data Index: 3219357 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.9230. Min Act: -0.1700
Data Index: 8314034 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.9230. Min Act: -0.1700
Data Index: 5635792 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.8605. Min Act: -0.1700
Data Index: 415825 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.8292. Min Act: -0.1700
Data Index: 184865 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.7667. Min Act: -0.1700
Data Index: 1245622 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.7980. Min Act: -0.1700
Data Index: 4656591 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.7667. Min Act: -0.1700
Data Index: 2598383 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.7355. Min Act: -0.1700
Data Index: 3350360 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.7355. Min Act: -0.1700
Data Index: 1674244 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.7355. Min Act: -0.1700
Data Index: 1582609 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.6730. Min Act: -0.1700
Data Index: 8181038 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.6730. Min Act: -0.1700
Data Index: 885695 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.7042. Min Act: -0.1700
Data Index: 374199 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.6730. Min Act: -0.1700
Data Index: 77965 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.6730. Min Act: -0.1700
Data Index: 6033728 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.6105. Min Act: -0.1700
Data Index: 1614611 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.6417. Min Act: -0.1700
Data Index: 3513471 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0167. Min Range: -7.0167
Max Act: 6.6105. Min Act: -0.1700
Data Index: 2753299 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19