Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6351 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0781. Min Range: -7.0781
Max Act: 7.0781. Min Act: -0.1700
Data Index: 1802715 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.9218. Min Act: -0.1700
Data Index: 4183265 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.9531. Min Act: -0.1700
Data Index: 3036459 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.6093. Min Act: -0.1700
Data Index: 2896245 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.4843. Min Act: -0.1700
Data Index: 945339 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.4531. Min Act: -0.1700
Data Index: 4264644 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.4843. Min Act: -0.1700
Data Index: 2573972 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.4531. Min Act: -0.1700
Data Index: 5028431 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.4218. Min Act: -0.1700
Data Index: 903816 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.3906. Min Act: -0.1700
Data Index: 6705041 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.2968. Min Act: -0.1700
Data Index: 7596845 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.2968. Min Act: -0.1700
Data Index: 1167607 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.2656. Min Act: -0.1700
Data Index: 7495768 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.2343. Min Act: -0.1700
Data Index: 4924454 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.2031. Min Act: -0.1700
Data Index: 7523068 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.1718. Min Act: -0.1700
Data Index: 7761006 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.2343. Min Act: -0.1700
Data Index: 1380645 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.1718. Min Act: -0.1700
Data Index: 8583185 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1182278 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0781. Min Range: -7.0781
Max Act: 6.1718. Min Act: -0.1700
Data Index: 2305182 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19