Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3749. Min Range: -7.3749
Max Act: 7.3749. Min Act: -0.1700
Data Index: 7012718 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3749. Min Range: -7.3749
Max Act: 7.3124. Min Act: -0.1700
Data Index: 4318230 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3749. Min Range: -7.3749
Max Act: 7.1561. Min Act: -0.1700
Data Index: 7360259 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3749. Min Range: -7.3749
Max Act: 7.0936. Min Act: -0.1700
Data Index: 8218749 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3749. Min Range: -7.3749
Max Act: 7.0624. Min Act: -0.1700
Data Index: 3882214 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.9999. Min Act: -0.1700
Data Index: 8792594 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.9686. Min Act: -0.1700
Data Index: 515365 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.9686. Min Act: -0.1700
Data Index: 8377660 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.8749. Min Act: -0.1700
Data Index: 6335626 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.8749. Min Act: -0.1700
Data Index: 5553242 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.7811. Min Act: -0.1700
Data Index: 7408394 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.8124. Min Act: -0.1700
Data Index: 4247125 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.7811. Min Act: -0.1700
Data Index: 7908178 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.8124. Min Act: -0.1700
Data Index: 5611121 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.8124. Min Act: -0.1700
Data Index: 1446083 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.7811. Min Act: -0.1700
Data Index: 5790008 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.7811. Min Act: -0.1700
Data Index: 5106347 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.7499. Min Act: -0.1700
Data Index: 7089076 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.7499. Min Act: -0.1700
Data Index: 7010556 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3749. Min Range: -7.3749
Max Act: 6.7499. Min Act: -0.1700
Data Index: 2491083 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19