Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5465 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.3007. Min Act: -0.1700
Data Index: 1792028 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.1757. Min Act: -0.1700
Data Index: 26455 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.2382. Min Act: -0.1700
Data Index: 6799175 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.0507. Min Act: -0.1700
Data Index: 295763 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.0507. Min Act: -0.1700
Data Index: 7428676 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.0507. Min Act: -0.1700
Data Index: 3987531 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.0507. Min Act: -0.1700
Data Index: 781193 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.9882. Min Act: -0.1700
Data Index: 6547057 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3007. Min Range: -8.3007
Max Act: 8.0507. Min Act: -0.1700
Data Index: 4545856 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.9570. Min Act: -0.1700
Data Index: 2330336 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.9570. Min Act: -0.1700
Data Index: 116197 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.9257. Min Act: -0.1700
Data Index: 946420 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8945. Min Act: -0.1700
Data Index: 7957225 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8632. Min Act: -0.1700
Data Index: 1515499 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8632. Min Act: -0.1700
Data Index: 2513774 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8945. Min Act: -0.1700
Data Index: 3701180 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8632. Min Act: -0.1700
Data Index: 1529082 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8632. Min Act: -0.1700
Data Index: 2715373 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8632. Min Act: -0.1700
Data Index: 5774621 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3007. Min Range: -8.3007
Max Act: 7.8320. Min Act: -0.1700
Data Index: 1515498 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19