Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1068 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0739. Min Act: -0.1700
Data Index: 340470 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0427. Min Act: -0.1700
Data Index: 2670338 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9802. Min Act: -0.1700
Data Index: 278091 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0114. Min Act: -0.1700
Data Index: 2005346 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0114. Min Act: -0.1700
Data Index: 3031430 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9802. Min Act: -0.1700
Data Index: 3503505 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9802. Min Act: -0.1700
Data Index: 818511 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9489. Min Act: -0.1700
Data Index: 8438272 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9489. Min Act: -0.1700
Data Index: 3346077 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9489. Min Act: -0.1700
Data Index: 6362640 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9489. Min Act: -0.1700
Data Index: 2652483 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 4209882 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 3311995 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 1377312 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 6131083 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 1139881 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9489. Min Act: -0.1700
Data Index: 4203253 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 2337190 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 7139170 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9177. Min Act: -0.1700
Data Index: 8119964 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19