Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 793 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.7171. Min Act: -0.1700
Data Index: 3933539 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.6858. Min Act: -0.1700
Data Index: 4567415 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.6546. Min Act: -0.1700
Data Index: 6019222 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.5921. Min Act: -0.1700
Data Index: 7585285 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.5296. Min Act: -0.1700
Data Index: 2514545 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.4983. Min Act: -0.1700
Data Index: 6564117 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.4671. Min Act: -0.1700
Data Index: 7992669 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.4358. Min Act: -0.1700
Data Index: 4013068 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.4046. Min Act: -0.1700
Data Index: 1009598 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3733. Min Act: -0.1700
Data Index: 771009 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3733. Min Act: -0.1700
Data Index: 8638089 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3733. Min Act: -0.1700
Data Index: 7077798 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3421. Min Act: -0.1700
Data Index: 4171971 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3421. Min Act: -0.1700
Data Index: 4557482 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3421. Min Act: -0.1700
Data Index: 2910132 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3108. Min Act: -0.1700
Data Index: 2077486 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3108. Min Act: -0.1700
Data Index: 3666254 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.3108. Min Act: -0.1700
Data Index: 6007435 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.2483. Min Act: -0.1700
Data Index: 6132278 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7171. Min Range: -5.7171
Max Act: 5.2796. Min Act: -0.1700
Data Index: 12312 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19