Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4392 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.3496. Min Act: -0.1700
Data Index: 7687352 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1621. Min Act: -0.1700
Data Index: 8282399 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0996. Min Act: -0.1700
Data Index: 54733 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0683. Min Act: -0.1700
Data Index: 805599 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0371. Min Act: -0.1700
Data Index: 987770 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0683. Min Act: -0.1700
Data Index: 4606322 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0371. Min Act: -0.1700
Data Index: 6831929 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0058. Min Act: -0.1700
Data Index: 7987456 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9746. Min Act: -0.1700
Data Index: 6359495 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9746. Min Act: -0.1700
Data Index: 1242212 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9746. Min Act: -0.1700
Data Index: 1974745 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9746. Min Act: -0.1700
Data Index: 2600788 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9433. Min Act: -0.1700
Data Index: 8776183 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9121. Min Act: -0.1700
Data Index: 8736453 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9121. Min Act: -0.1700
Data Index: 2376784 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9121. Min Act: -0.1700
Data Index: 1328148 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.9121. Min Act: -0.1700
Data Index: 3870048 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.8808. Min Act: -0.1700
Data Index: 515308 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7220480 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3496. Min Range: -5.3496
Max Act: 4.8808. Min Act: -0.1700
Data Index: 2807159 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19