Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 383 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.4543. Min Act: -0.1700
Data Index: 3359419 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.4230. Min Act: -0.1700
Data Index: 8672711 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.3293. Min Act: -0.1700
Data Index: 5362157 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2980. Min Act: -0.1700
Data Index: 3619398 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2980. Min Act: -0.1700
Data Index: 507422 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.3293. Min Act: -0.1700
Data Index: 1194320 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2355. Min Act: -0.1700
Data Index: 8016019 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2355. Min Act: -0.1700
Data Index: 7643734 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2043. Min Act: -0.1700
Data Index: 3785737 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2043. Min Act: -0.1700
Data Index: 4656623 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2043. Min Act: -0.1700
Data Index: 7691042 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2043. Min Act: -0.1700
Data Index: 4553460 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2043. Min Act: -0.1700
Data Index: 7571974 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2043. Min Act: -0.1700
Data Index: 3094594 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.2043. Min Act: -0.1700
Data Index: 5471349 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.1730. Min Act: -0.1700
Data Index: 4190321 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.1418. Min Act: -0.1700
Data Index: 6298654 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.1418. Min Act: -0.1700
Data Index: 4928602 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.1418. Min Act: -0.1700
Data Index: 2161290 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4543. Min Range: -4.4543
Max Act: 4.1418. Min Act: -0.1700
Data Index: 1025018 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19