Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4596 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.8952. Min Act: -0.1700
Data Index: 6622612 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.6452. Min Act: -0.1700
Data Index: 5426569 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.6140. Min Act: -0.1700
Data Index: 1399748 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.6140. Min Act: -0.1700
Data Index: 2191090 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.6140. Min Act: -0.1700
Data Index: 4321196 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.5827. Min Act: -0.1700
Data Index: 543144 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.5515. Min Act: -0.1700
Data Index: 518741 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.5202. Min Act: -0.1700
Data Index: 4385401 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.5202. Min Act: -0.1700
Data Index: 6724532 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.4577. Min Act: -0.1700
Data Index: 6371697 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.4577. Min Act: -0.1700
Data Index: 7142446 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.4265. Min Act: -0.1700
Data Index: 8039542 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3640. Min Act: -0.1700
Data Index: 6145644 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3327. Min Act: -0.1700
Data Index: 1841214 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3327. Min Act: -0.1700
Data Index: 4126961 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 7847072 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3327. Min Act: -0.1700
Data Index: 4021223 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 1089117 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 5056733 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8952. Min Range: -6.8952
Max Act: 6.3015. Min Act: -0.1700
Data Index: 6394511 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19