Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.9175. Min Act: -0.1700
Data Index: 6011491 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.7925. Min Act: -0.1700
Data Index: 6586085 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.5737. Min Act: -0.1700
Data Index: 3037864 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.5425. Min Act: -0.1700
Data Index: 2938061 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.5112. Min Act: -0.1700
Data Index: 3878076 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.5112. Min Act: -0.1700
Data Index: 6024004 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.4487. Min Act: -0.1700
Data Index: 7078362 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.4175. Min Act: -0.1700
Data Index: 810696 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.3237. Min Act: -0.1700
Data Index: 1330090 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.3237. Min Act: -0.1700
Data Index: 2604546 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.3550. Min Act: -0.1700
Data Index: 3851066 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.3550. Min Act: -0.1700
Data Index: 1744167 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2925. Min Act: -0.1700
Data Index: 7334945 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2925. Min Act: -0.1700
Data Index: 5633206 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2612. Min Act: -0.1700
Data Index: 2304650 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2612. Min Act: -0.1700
Data Index: 1330096 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2612. Min Act: -0.1700
Data Index: 4712925 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2300. Min Act: -0.1700
Data Index: 4198007 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2300. Min Act: -0.1700
Data Index: 2965797 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9175. Min Range: -7.9175
Max Act: 7.2300. Min Act: -0.1700
Data Index: 2274261 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19