Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1177 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.4288. Min Act: -0.1700
Data Index: 4639183 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.4125. Min Act: -0.1700
Data Index: 1609087 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.3307. Min Act: -0.1700
Data Index: 7461503 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2814. Min Act: -0.1700
Data Index: 144741 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2814. Min Act: -0.1700
Data Index: 7461501 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2484. Min Act: -0.1700
Data Index: 6355899 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2153. Min Act: -0.1700
Data Index: 624448 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1987. Min Act: -0.1700
Data Index: 3350945 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1987. Min Act: -0.1700
Data Index: 662580 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2153. Min Act: -0.1700
Data Index: 2189069 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2318. Min Act: -0.1700
Data Index: 1905195 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2153. Min Act: -0.1700
Data Index: 6970797 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1987. Min Act: -0.1700
Data Index: 8136956 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1987. Min Act: -0.1700
Data Index: 7196167 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1987. Min Act: -0.1700
Data Index: 2189070 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1987. Min Act: -0.1700
Data Index: 1497818 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.2153. Min Act: -0.1700
Data Index: 7245390 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1987. Min Act: -0.1700
Data Index: 5136076 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1821. Min Act: -0.1700
Data Index: 4066247 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4288. Min Range: -2.4288
Max Act: 2.1821. Min Act: -0.1700
Data Index: 1928671 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19