Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.5167. Min Act: -0.1700
Data Index: 3011112 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.4542. Min Act: -0.1700
Data Index: 4140749 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.4230. Min Act: -0.1700
Data Index: 1220209 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.3292. Min Act: -0.1700
Data Index: 6937545 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.3292. Min Act: -0.1700
Data Index: 7974263 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2980. Min Act: -0.1700
Data Index: 1365582 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2980. Min Act: -0.1700
Data Index: 315874 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2667. Min Act: -0.1700
Data Index: 2912721 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2667. Min Act: -0.1700
Data Index: 7095613 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2667. Min Act: -0.1700
Data Index: 7656180 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2355. Min Act: -0.1700
Data Index: 4619604 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2355. Min Act: -0.1700
Data Index: 2244813 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2042. Min Act: -0.1700
Data Index: 5294531 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2042. Min Act: -0.1700
Data Index: 3356774 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2042. Min Act: -0.1700
Data Index: 5197924 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.2042. Min Act: -0.1700
Data Index: 5317540 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.1730. Min Act: -0.1700
Data Index: 3286906 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.1730. Min Act: -0.1700
Data Index: 3315187 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.1105. Min Act: -0.1700
Data Index: 4771901 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5167. Min Range: -5.5167
Max Act: 5.1417. Min Act: -0.1700
Data Index: 3703208 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19