Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4819. Min Range: -8.4819
Max Act: 8.4819. Min Act: -0.1700
Data Index: 6677138 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.9194. Min Act: -0.1700
Data Index: 5600573 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.9194. Min Act: -0.1700
Data Index: 2268910 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.8569. Min Act: -0.1700
Data Index: 246334 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.8569. Min Act: -0.1700
Data Index: 5468304 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.9194. Min Act: -0.1700
Data Index: 3864806 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.7944. Min Act: -0.1700
Data Index: 646607 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.7319. Min Act: -0.1700
Data Index: 6677136 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.7319. Min Act: -0.1700
Data Index: 885085 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.7944. Min Act: -0.1700
Data Index: 6677122 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.6694. Min Act: -0.1700
Data Index: 7575454 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.6694. Min Act: -0.1700
Data Index: 7829311 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.6694. Min Act: -0.1700
Data Index: 3150012 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.6069. Min Act: -0.1700
Data Index: 1283196 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.5444. Min Act: -0.1700
Data Index: 3557596 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.4819. Min Act: -0.1700
Data Index: 3123448 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.4507. Min Act: -0.1700
Data Index: 4212848 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.4507. Min Act: -0.1700
Data Index: 7653599 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.4507. Min Act: -0.1700
Data Index: 1699757 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4819. Min Range: -8.4819
Max Act: 7.4507. Min Act: -0.1700
Data Index: 3989051 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19