Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3834 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0921. Min Range: -9.0921
Max Act: 9.0921. Min Act: -0.1700
Data Index: 3330224 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0921. Min Range: -9.0921
Max Act: 9.0921. Min Act: -0.1700
Data Index: 7225731 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.9671. Min Act: -0.1700
Data Index: 2219505 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.9671. Min Act: -0.1700
Data Index: 3877860 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.9046. Min Act: -0.1700
Data Index: 1355000 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.8421. Min Act: -0.1700
Data Index: 2892951 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.8421. Min Act: -0.1700
Data Index: 6072317 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.8421. Min Act: -0.1700
Data Index: 3916122 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.7796. Min Act: -0.1700
Data Index: 3524661 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.7171. Min Act: -0.1700
Data Index: 6743149 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.7171. Min Act: -0.1700
Data Index: 3921560 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.6546. Min Act: -0.1700
Data Index: 3877857 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.6546. Min Act: -0.1700
Data Index: 2892952 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.5921. Min Act: -0.1700
Data Index: 5647339 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.5296. Min Act: -0.1700
Data Index: 8571956 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.5921. Min Act: -0.1700
Data Index: 372107 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.5296. Min Act: -0.1700
Data Index: 865609 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.4046. Min Act: -0.1700
Data Index: 4804036 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.4046. Min Act: -0.1700
Data Index: 4695704 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0921. Min Range: -9.0921
Max Act: 8.3421. Min Act: -0.1700
Data Index: 4525537 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19