Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3277 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4860. Min Range: -6.4860
Max Act: 6.4860. Min Act: -0.1700
Data Index: 7811246 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4860. Min Range: -6.4860
Max Act: 6.3297. Min Act: -0.1700
Data Index: 7528143 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4860. Min Range: -6.4860
Max Act: 6.0485. Min Act: -0.1700
Data Index: 4473523 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4860. Min Range: -6.4860
Max Act: 6.0172. Min Act: -0.1700
Data Index: 2632630 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.9547. Min Act: -0.1700
Data Index: 3491050 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.9547. Min Act: -0.1700
Data Index: 8167571 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.9235. Min Act: -0.1700
Data Index: 5119472 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.9547. Min Act: -0.1700
Data Index: 5145491 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.9547. Min Act: -0.1700
Data Index: 110146 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.8922. Min Act: -0.1700
Data Index: 7989425 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.8610. Min Act: -0.1700
Data Index: 8287688 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.8922. Min Act: -0.1700
Data Index: 5124194 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.8610. Min Act: -0.1700
Data Index: 4295450 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.8610. Min Act: -0.1700
Data Index: 4684655 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.8610. Min Act: -0.1700
Data Index: 6167578 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.8297. Min Act: -0.1700
Data Index: 2463027 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.7985. Min Act: -0.1700
Data Index: 6299289 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.7985. Min Act: -0.1700
Data Index: 5361224 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.7672. Min Act: -0.1700
Data Index: 608278 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4860. Min Range: -6.4860
Max Act: 5.7672. Min Act: -0.1700
Data Index: 1142948 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19