Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 825 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2349. Min Range: -6.2349
Max Act: 6.2349. Min Act: -0.1700
Data Index: 5024746 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2349. Min Range: -6.2349
Max Act: 6.0787. Min Act: -0.1700
Data Index: 4794763 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8912. Min Act: -0.1700
Data Index: 1443323 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8599. Min Act: -0.1700
Data Index: 2280217 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8599. Min Act: -0.1700
Data Index: 3114772 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8287. Min Act: -0.1700
Data Index: 2063948 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7974. Min Act: -0.1700
Data Index: 3668234 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7662. Min Act: -0.1700
Data Index: 2098769 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7974. Min Act: -0.1700
Data Index: 2347848 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.8287. Min Act: -0.1700
Data Index: 2550711 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7349. Min Act: -0.1700
Data Index: 7067818 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7349. Min Act: -0.1700
Data Index: 6410321 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.7037. Min Act: -0.1700
Data Index: 2591194 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.6724. Min Act: -0.1700
Data Index: 8462189 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.6724. Min Act: -0.1700
Data Index: 8210334 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.6412. Min Act: -0.1700
Data Index: 5064950 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.6412. Min Act: -0.1700
Data Index: 2826234 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.6099. Min Act: -0.1700
Data Index: 1386414 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.6412. Min Act: -0.1700
Data Index: 5586923 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2349. Min Range: -6.2349
Max Act: 5.6099. Min Act: -0.1700
Data Index: 6960024 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19