Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6350 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.9530. Min Act: -0.1700
Data Index: 7190590 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.8905. Min Act: -0.1700
Data Index: 6309166 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.7342. Min Act: -0.1700
Data Index: 834778 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.6717. Min Act: -0.1700
Data Index: 6701937 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.6405. Min Act: -0.1700
Data Index: 4431190 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.5467. Min Act: -0.1700
Data Index: 886610 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.5155. Min Act: -0.1700
Data Index: 5704052 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.5155. Min Act: -0.1700
Data Index: 1344705 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.4530. Min Act: -0.1700
Data Index: 3494195 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.4217. Min Act: -0.1700
Data Index: 4525966 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.4217. Min Act: -0.1700
Data Index: 982145 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.3905. Min Act: -0.1700
Data Index: 4072421 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.3905. Min Act: -0.1700
Data Index: 2240834 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.4217. Min Act: -0.1700
Data Index: 6144488 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.3905. Min Act: -0.1700
Data Index: 368534 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.3905. Min Act: -0.1700
Data Index: 1297135 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.3280. Min Act: -0.1700
Data Index: 312554 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.2967. Min Act: -0.1700
Data Index: 2616214 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.2967. Min Act: -0.1700
Data Index: 532016 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9530. Min Range: -5.9530
Max Act: 5.3280. Min Act: -0.1700
Data Index: 1330170 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19