Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.9569. Min Act: -0.1700
Data Index: 1991070 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.5194. Min Act: -0.1700
Data Index: 5015867 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.4569. Min Act: -0.1700
Data Index: 1246212 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.4569. Min Act: -0.1700
Data Index: 5903495 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.4569. Min Act: -0.1700
Data Index: 4008209 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.3944. Min Act: -0.1700
Data Index: 4277736 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.3319. Min Act: -0.1700
Data Index: 1942057 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.2694. Min Act: -0.1700
Data Index: 7000842 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.2694. Min Act: -0.1700
Data Index: 8758199 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.2069. Min Act: -0.1700
Data Index: 3052063 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.2069. Min Act: -0.1700
Data Index: 4879632 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.2069. Min Act: -0.1700
Data Index: 797118 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.1444. Min Act: -0.1700
Data Index: 2986826 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.1444. Min Act: -0.1700
Data Index: 7667872 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.0819. Min Act: -0.1700
Data Index: 3319622 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.0819. Min Act: -0.1700
Data Index: 5325655 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.0819. Min Act: -0.1700
Data Index: 7590738 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.0194. Min Act: -0.1700
Data Index: 3024563 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.0194. Min Act: -0.1700
Data Index: 7762088 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9569. Min Range: -9.9569
Max Act: 9.0194. Min Act: -0.1700
Data Index: 8227655 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19