Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.5177. Min Act: -0.1700
Data Index: 4778388 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.4552. Min Act: -0.1700
Data Index: 3495063 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.3302. Min Act: -0.1700
Data Index: 5755616 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.3927. Min Act: -0.1700
Data Index: 5029867 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.3302. Min Act: -0.1697
Data Index: 975432 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.2677. Min Act: -0.1700
Data Index: 5045956 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.2052. Min Act: -0.1700
Data Index: 8303395 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.2052. Min Act: -0.1700
Data Index: 8350786 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.2052. Min Act: -0.1700
Data Index: 3297801 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.2052. Min Act: -0.1700
Data Index: 7979232 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.0802. Min Act: -0.1700
Data Index: 8115685 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.1427. Min Act: -0.1700
Data Index: 5372586 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.0177. Min Act: -0.1700
Data Index: 4312236 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.0177. Min Act: -0.1700
Data Index: 7021145 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5177. Min Range: -9.5177
Max Act: 9.0177. Min Act: -0.1700
Data Index: 1583853 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5177. Min Range: -9.5177
Max Act: 8.9552. Min Act: -0.1700
Data Index: 4159207 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5177. Min Range: -9.5177
Max Act: 8.8927. Min Act: -0.1700
Data Index: 2189474 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5177. Min Range: -9.5177
Max Act: 8.8302. Min Act: -0.1700
Data Index: 4956489 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5177. Min Range: -9.5177
Max Act: 8.8927. Min Act: -0.1700
Data Index: 3157788 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5177. Min Range: -9.5177
Max Act: 8.8927. Min Act: -0.1700
Data Index: 5157407 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19