Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.6832. Min Act: -0.1700
Data Index: 5859054 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.6207. Min Act: -0.1700
Data Index: 4043710 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.2457. Min Act: -0.1700
Data Index: 5437019 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.2145. Min Act: -0.1700
Data Index: 543256 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.2145. Min Act: -0.1700
Data Index: 4077564 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.1832. Min Act: -0.1700
Data Index: 4291393 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.1520. Min Act: -0.1700
Data Index: 1543951 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.1207. Min Act: -0.1700
Data Index: 8548283 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.1520. Min Act: -0.1700
Data Index: 3119695 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0895. Min Act: -0.1700
Data Index: 3121527 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0582. Min Act: -0.1700
Data Index: 2406782 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0895. Min Act: -0.1700
Data Index: 7201347 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0582. Min Act: -0.1700
Data Index: 1262129 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0270. Min Act: -0.1700
Data Index: 7103941 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0582. Min Act: -0.1700
Data Index: 243856 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6832. Min Range: -5.6832
Max Act: 4.9957. Min Act: -0.1700
Data Index: 863995 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0270. Min Act: -0.1700
Data Index: 3333045 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6832. Min Range: -5.6832
Max Act: 4.9957. Min Act: -0.1700
Data Index: 3910361 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0270. Min Act: -0.1700
Data Index: 5822449 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6832. Min Range: -5.6832
Max Act: 5.0270. Min Act: -0.1700
Data Index: 5319138 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19