Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.9268. Min Act: -0.1700
Data Index: 1315184 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.6453. Min Act: -0.1700
Data Index: 4843863 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.4731. Min Act: -0.1700
Data Index: 13783 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.4731. Min Act: -0.1700
Data Index: 4805727 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.4574. Min Act: -0.1700
Data Index: 5237546 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.4261. Min Act: -0.1700
Data Index: 4766504 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.4104. Min Act: -0.1700
Data Index: 7214978 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.4104. Min Act: -0.1700
Data Index: 2977546 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3947. Min Act: -0.1700
Data Index: 8308125 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3947. Min Act: -0.1700
Data Index: 7665819 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.4104. Min Act: -0.1700
Data Index: 5993377 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3633. Min Act: -0.1700
Data Index: 1219984 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3790. Min Act: -0.1700
Data Index: 877877 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3633. Min Act: -0.1700
Data Index: 8614005 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3633. Min Act: -0.1700
Data Index: 13779 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3633. Min Act: -0.1700
Data Index: 2269550 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3163. Min Act: -0.1700
Data Index: 8308119 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3163. Min Act: -0.1700
Data Index: 229413 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3320. Min Act: -0.1700
Data Index: 8308117 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9268. Min Range: -3.9268
Max Act: 3.3163. Min Act: -0.1700
Data Index: 699772 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19