Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.5093. Min Act: -0.1700
Data Index: 5578543 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.3531. Min Act: -0.1700
Data Index: 81406 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.3218. Min Act: -0.1700
Data Index: 3969261 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.2280. Min Act: -0.1700
Data Index: 5057308 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.2593. Min Act: -0.1700
Data Index: 5584232 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.2280. Min Act: -0.1700
Data Index: 6016850 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1655. Min Act: -0.1700
Data Index: 4919865 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1968. Min Act: -0.1700
Data Index: 6766572 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1655. Min Act: -0.1700
Data Index: 3913201 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1655. Min Act: -0.1700
Data Index: 845306 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1343. Min Act: -0.1700
Data Index: 6125940 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1343. Min Act: -0.1700
Data Index: 3146255 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1030. Min Act: -0.1700
Data Index: 1767670 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1030. Min Act: -0.1700
Data Index: 1121999 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1030. Min Act: -0.1700
Data Index: 2828315 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1030. Min Act: -0.1700
Data Index: 5244717 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.0718. Min Act: -0.1700
Data Index: 7608990 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.1030. Min Act: -0.1700
Data Index: 2377680 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.0718. Min Act: -0.1700
Data Index: 4137031 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5093. Min Range: -4.5093
Max Act: 4.0405. Min Act: -0.1700
Data Index: 165276 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19