Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.4052. Min Act: -0.1700
Data Index: 2045725 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.3114. Min Act: -0.1700
Data Index: 5645299 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.3114. Min Act: -0.1700
Data Index: 8131936 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.3114. Min Act: -0.1700
Data Index: 1816749 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2802. Min Act: -0.1700
Data Index: 2452785 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2802. Min Act: -0.1700
Data Index: 925628 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2802. Min Act: -0.1700
Data Index: 2695256 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2802. Min Act: -0.1700
Data Index: 4177967 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2489. Min Act: -0.1700
Data Index: 5666924 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2489. Min Act: -0.1700
Data Index: 7652601 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2177. Min Act: -0.1700
Data Index: 3677399 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2489. Min Act: -0.1700
Data Index: 5053747 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2489. Min Act: -0.1700
Data Index: 8328904 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2177. Min Act: -0.1700
Data Index: 2340417 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.1864. Min Act: -0.1700
Data Index: 2311351 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2177. Min Act: -0.1700
Data Index: 8250960 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2177. Min Act: -0.1700
Data Index: 7891480 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.2177. Min Act: -0.1700
Data Index: 5960534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.1864. Min Act: -0.1700
Data Index: 5827958 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4052. Min Range: -4.4052
Max Act: 4.1864. Min Act: -0.1700
Data Index: 4749268 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19