Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.3533. Min Act: -0.1700
Data Index: 8529435 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.3219. Min Act: -0.1700
Data Index: 3993210 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2434. Min Act: -0.1700
Data Index: 7175422 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2434. Min Act: -0.1700
Data Index: 8555470 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2120. Min Act: -0.1700
Data Index: 7194263 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2277. Min Act: -0.1700
Data Index: 5890105 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2434. Min Act: -0.1700
Data Index: 5595109 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2120. Min Act: -0.1700
Data Index: 5899566 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1805. Min Act: -0.1700
Data Index: 5981681 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1963. Min Act: -0.1700
Data Index: 1142040 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1963. Min Act: -0.1700
Data Index: 634472 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1963. Min Act: -0.1700
Data Index: 5539859 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1648. Min Act: -0.1700
Data Index: 2939630 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1805. Min Act: -0.1700
Data Index: 3098446 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1648. Min Act: -0.1700
Data Index: 4053022 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1333. Min Act: -0.1700
Data Index: 1792558 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1176. Min Act: -0.1700
Data Index: 2130049 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1176. Min Act: -0.1700
Data Index: 1243784 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.0861. Min Act: -0.1700
Data Index: 1624019 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1018. Min Act: -0.1700
Data Index: 1337845 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19