Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 7014193 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.8953. Min Act: -0.1700
Data Index: 571911 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.8015. Min Act: -0.1700
Data Index: 1982961 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.8328. Min Act: -0.1700
Data Index: 346948 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.7703. Min Act: -0.1700
Data Index: 4148365 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.7703. Min Act: -0.1700
Data Index: 3499347 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.7078. Min Act: -0.1700
Data Index: 8058135 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.7078. Min Act: -0.1700
Data Index: 6198181 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.6765. Min Act: -0.1700
Data Index: 5911192 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.6453. Min Act: -0.1700
Data Index: 6406233 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.6453. Min Act: -0.1700
Data Index: 6066083 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.6140. Min Act: -0.1700
Data Index: 6263044 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.6140. Min Act: -0.1700
Data Index: 3919310 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.6140. Min Act: -0.1700
Data Index: 4020048 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.5828. Min Act: -0.1700
Data Index: 2872028 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.5828. Min Act: -0.1700
Data Index: 6047909 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.5515. Min Act: -0.1700
Data Index: 3675514 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.5515. Min Act: -0.1700
Data Index: 1015271 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.5515. Min Act: -0.1700
Data Index: 931133 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8953. Min Range: -5.8953
Max Act: 5.5515. Min Act: -0.1700
Data Index: 4020039 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19