Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6912. Min Act: -0.1700
Data Index: 5243210 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.7225. Min Act: -0.1700
Data Index: 4841837 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.7068. Min Act: -0.1700
Data Index: 2237688 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6912. Min Act: -0.1700
Data Index: 4398697 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.7068. Min Act: -0.1700
Data Index: 3953770 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6912. Min Act: -0.1700
Data Index: 5270476 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6442. Min Act: -0.1700
Data Index: 3941016 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6599. Min Act: -0.1700
Data Index: 4826033 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6286. Min Act: -0.1700
Data Index: 340748 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6442. Min Act: -0.1700
Data Index: 3004569 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6442. Min Act: -0.1700
Data Index: 6172932 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6599. Min Act: -0.1700
Data Index: 5045557 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6129. Min Act: -0.1700
Data Index: 994230 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6129. Min Act: -0.1700
Data Index: 7085021 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6286. Min Act: -0.1700
Data Index: 1248546 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5816. Min Act: -0.1700
Data Index: 6027098 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6286. Min Act: -0.1700
Data Index: 5870479 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5973. Min Act: -0.1700
Data Index: 5877879 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5973. Min Act: -0.1700
Data Index: 3767676 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5973. Min Act: -0.1700
Data Index: 7841797 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19