Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.5060. Min Act: -0.1700
Data Index: 7481328 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.4435. Min Act: -0.1699
Data Index: 3409603 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.4435. Min Act: -0.1700
Data Index: 4136259 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.3497. Min Act: -0.1700
Data Index: 7595999 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.3497. Min Act: -0.1700
Data Index: 545804 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.3184. Min Act: -0.1700
Data Index: 242934 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.3184. Min Act: -0.1700
Data Index: 3478882 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.3184. Min Act: -0.1700
Data Index: 7154992 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.3184. Min Act: -0.1700
Data Index: 4584950 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.3184. Min Act: -0.1700
Data Index: 6521336 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2872. Min Act: -0.1700
Data Index: 1762674 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2872. Min Act: -0.1700
Data Index: 8084866 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2559. Min Act: -0.1700
Data Index: 1195349 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2559. Min Act: -0.1700
Data Index: 964633 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2559. Min Act: -0.1700
Data Index: 4504649 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2559. Min Act: -0.1700
Data Index: 1890167 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2559. Min Act: -0.1700
Data Index: 3490846 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2559. Min Act: -0.1700
Data Index: 8087385 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2247. Min Act: -0.1700
Data Index: 5007278 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5060. Min Range: -4.5060
Max Act: 4.2559. Min Act: -0.1700
Data Index: 680598 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19