Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2010 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.6085. Min Act: -0.1700
Data Index: 499204 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.5772. Min Act: -0.1700
Data Index: 5246147 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.4835. Min Act: -0.1700
Data Index: 4203681 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.4835. Min Act: -0.1700
Data Index: 3601747 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.4835. Min Act: -0.1700
Data Index: 1975376 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.4522. Min Act: -0.1700
Data Index: 2125543 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.4210. Min Act: -0.1700
Data Index: 6948628 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.4210. Min Act: -0.1700
Data Index: 1164325 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3897. Min Act: -0.1700
Data Index: 8683276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3897. Min Act: -0.1699
Data Index: 8073926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3585. Min Act: -0.1700
Data Index: 4799278 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3897. Min Act: -0.1700
Data Index: 3012656 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3897. Min Act: -0.1700
Data Index: 3470377 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3897. Min Act: -0.1700
Data Index: 4184983 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3585. Min Act: -0.1700
Data Index: 2084682 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3585. Min Act: -0.1700
Data Index: 8580523 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3585. Min Act: -0.1700
Data Index: 4612649 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.3272. Min Act: -0.1700
Data Index: 790802 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.2960. Min Act: -0.1700
Data Index: 4590020 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6085. Min Range: -6.6085
Max Act: 6.2960. Min Act: -0.1700
Data Index: 3991534 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19