Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.1286. Min Act: -0.1700
Data Index: 2850242 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.1286. Min Act: -0.1700
Data Index: 3531381 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.0974. Min Act: -0.1700
Data Index: 4837471 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.0661. Min Act: -0.1700
Data Index: 2850243 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.0349. Min Act: -0.1700
Data Index: 4422759 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.0349. Min Act: -0.1700
Data Index: 3568941 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.0349. Min Act: -0.1700
Data Index: 1014919 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.0036. Min Act: -0.1700
Data Index: 7958042 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1286. Min Range: -6.1286
Max Act: 6.0036. Min Act: -0.1700
Data Index: 7002946 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9724. Min Act: -0.1700
Data Index: 1742262 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9724. Min Act: -0.1700
Data Index: 4661036 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9724. Min Act: -0.1700
Data Index: 8294952 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9724. Min Act: -0.1700
Data Index: 6063739 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9411. Min Act: -0.1700
Data Index: 805923 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9099. Min Act: -0.1700
Data Index: 1379065 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.8786. Min Act: -0.1700
Data Index: 2923678 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9099. Min Act: -0.1700
Data Index: 5325677 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9099. Min Act: -0.1700
Data Index: 5610148 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9099. Min Act: -0.1700
Data Index: 3568937 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1286. Min Range: -6.1286
Max Act: 5.9099. Min Act: -0.1700
Data Index: 29361 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19