Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.7286. Min Act: -0.1700
Data Index: 7848010 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.5099. Min Act: -0.1700
Data Index: 725058 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.4474. Min Act: -0.1700
Data Index: 8122661 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.4474. Min Act: -0.1700
Data Index: 8212443 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.4161. Min Act: -0.1700
Data Index: 4952278 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.4161. Min Act: -0.1700
Data Index: 8645596 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.4161. Min Act: -0.1700
Data Index: 849225 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.3849. Min Act: -0.1700
Data Index: 3227080 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.3224. Min Act: -0.1700
Data Index: 2505114 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.2911. Min Act: -0.1700
Data Index: 2455274 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.2911. Min Act: -0.1700
Data Index: 4144591 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.1974. Min Act: -0.1700
Data Index: 7138261 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.2286. Min Act: -0.1700
Data Index: 1987652 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.2286. Min Act: -0.1700
Data Index: 7434167 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.1974. Min Act: -0.1700
Data Index: 6897840 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.1974. Min Act: -0.1700
Data Index: 415624 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.1974. Min Act: -0.1700
Data Index: 4270974 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.1661. Min Act: -0.1700
Data Index: 6755263 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.1661. Min Act: -0.1700
Data Index: 7117322 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7286. Min Range: -6.7286
Max Act: 6.1661. Min Act: -0.1700
Data Index: 2890127 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19