Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.5297. Min Act: -0.1700
Data Index: 1849197 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.4047. Min Act: -0.1700
Data Index: 4280719 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.3422. Min Act: -0.1700
Data Index: 1530443 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.3422. Min Act: -0.1700
Data Index: 3336250 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.2797. Min Act: -0.1700
Data Index: 1371220 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.2797. Min Act: -0.1700
Data Index: 7399399 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.2172. Min Act: -0.1700
Data Index: 2210664 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.2172. Min Act: -0.1700
Data Index: 7324155 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.0922. Min Act: -0.1700
Data Index: 7171945 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.0922. Min Act: -0.1700
Data Index: 4009493 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.0297. Min Act: -0.1700
Data Index: 2907788 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.0297. Min Act: -0.1700
Data Index: 7084975 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5297. Min Range: -9.5297
Max Act: 8.9672. Min Act: -0.1700
Data Index: 2373793 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.0297. Min Act: -0.1700
Data Index: 8138254 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.0297. Min Act: -0.1700
Data Index: 8598671 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5297. Min Range: -9.5297
Max Act: 9.0297. Min Act: -0.1700
Data Index: 2698774 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5297. Min Range: -9.5297
Max Act: 8.9672. Min Act: -0.1700
Data Index: 7494422 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5297. Min Range: -9.5297
Max Act: 8.9672. Min Act: -0.1700
Data Index: 6049246 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5297. Min Range: -9.5297
Max Act: 8.9672. Min Act: -0.1700
Data Index: 6907638 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5297. Min Range: -9.5297
Max Act: 8.9672. Min Act: -0.1700
Data Index: 3833122 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19