Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.6796. Min Act: -0.1700
Data Index: 3910710 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.6476. Min Act: -0.1700
Data Index: 8552291 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.5671. Min Act: -0.1700
Data Index: 4359260 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.5671. Min Act: -0.1700
Data Index: 5923373 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.5187. Min Act: -0.1700
Data Index: 127888 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4863. Min Act: -0.1700
Data Index: 767143 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.5025. Min Act: -0.1700
Data Index: 5568899 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.5187. Min Act: -0.1700
Data Index: 206350 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.5187. Min Act: -0.1700
Data Index: 3465519 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4538. Min Act: -0.1700
Data Index: 6604804 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4538. Min Act: -0.1700
Data Index: 5744672 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4538. Min Act: -0.1700
Data Index: 161391 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4538. Min Act: -0.1700
Data Index: 3151448 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4538. Min Act: -0.1700
Data Index: 334410 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4538. Min Act: -0.1700
Data Index: 1950400 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4213. Min Act: -0.1700
Data Index: 3275103 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4538. Min Act: -0.1700
Data Index: 5625860 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4375. Min Act: -0.1700
Data Index: 7098647 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4375. Min Act: -0.1700
Data Index: 2175642 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6796. Min Range: -2.6796
Max Act: 2.4213. Min Act: -0.1700
Data Index: 1781305 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19