Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.5801. Min Act: -0.1700
Data Index: 417550 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7060449 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.4551. Min Act: -0.1700
Data Index: 1906388 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.4864. Min Act: -0.1700
Data Index: 7997511 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.4239. Min Act: -0.1700
Data Index: 850230 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3926. Min Act: -0.1700
Data Index: 4198827 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.4239. Min Act: -0.1700
Data Index: 661213 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3926. Min Act: -0.1700
Data Index: 1496020 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3926. Min Act: -0.1700
Data Index: 4200890 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3926. Min Act: -0.1700
Data Index: 2354036 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3926. Min Act: -0.1700
Data Index: 4915779 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3614. Min Act: -0.1700
Data Index: 3923540 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3614. Min Act: -0.1700
Data Index: 4373130 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3301. Min Act: -0.1700
Data Index: 862191 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3301. Min Act: -0.1700
Data Index: 2917050 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3301. Min Act: -0.1700
Data Index: 5965524 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.3614. Min Act: -0.1700
Data Index: 5513742 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.2989. Min Act: -0.1700
Data Index: 6340601 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.2989. Min Act: -0.1700
Data Index: 1715129 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5801. Min Range: -5.5801
Max Act: 5.2989. Min Act: -0.1700
Data Index: 4616931 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19