Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4279 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.4093. Min Act: -0.1700
Data Index: 5969837 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.3151. Min Act: -0.1700
Data Index: 2087846 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2837. Min Act: -0.1700
Data Index: 7762040 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2523. Min Act: -0.1700
Data Index: 2543116 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2523. Min Act: -0.1700
Data Index: 3511541 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2366. Min Act: -0.1700
Data Index: 2385410 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2366. Min Act: -0.1700
Data Index: 6833997 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2366. Min Act: -0.1700
Data Index: 6408112 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2209. Min Act: -0.1700
Data Index: 9550 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2366. Min Act: -0.1700
Data Index: 1724843 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2209. Min Act: -0.1700
Data Index: 4091157 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2052. Min Act: -0.1700
Data Index: 1648763 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2052. Min Act: -0.1700
Data Index: 6063003 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2209. Min Act: -0.1700
Data Index: 3126857 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2052. Min Act: -0.1700
Data Index: 4146394 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.2052. Min Act: -0.1700
Data Index: 3511531 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.1737. Min Act: -0.1700
Data Index: 2346900 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.1894. Min Act: -0.1700
Data Index: 1850891 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.1737. Min Act: -0.1700
Data Index: 5852860 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4093. Min Range: -3.4093
Max Act: 3.1737. Min Act: -0.1700
Data Index: 4535398 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19