Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4862 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.8670. Min Act: -0.1700
Data Index: 1158040 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4920. Min Act: -0.1700
Data Index: 6308235 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.5545. Min Act: -0.1700
Data Index: 2111254 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.5545. Min Act: -0.1700
Data Index: 4968606 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4920. Min Act: -0.1700
Data Index: 337125 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4920. Min Act: -0.1700
Data Index: 5063555 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4920. Min Act: -0.1700
Data Index: 3763170 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4920. Min Act: -0.1700
Data Index: 3548078 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4607. Min Act: -0.1700
Data Index: 1729805 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4607. Min Act: -0.1700
Data Index: 4854815 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4607. Min Act: -0.1700
Data Index: 6964878 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4607. Min Act: -0.1700
Data Index: 7171959 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4607. Min Act: -0.1700
Data Index: 2551530 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4295. Min Act: -0.1700
Data Index: 3434773 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4295. Min Act: -0.1700
Data Index: 695993 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4295. Min Act: -0.1700
Data Index: 5464085 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4295. Min Act: -0.1700
Data Index: 2802201 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4295. Min Act: -0.1700
Data Index: 6119902 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4295. Min Act: -0.1700
Data Index: 3786701 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8670. Min Range: -7.8670
Max Act: 7.4295. Min Act: -0.1700
Data Index: 2558347 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19