Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0089. Min Range: -7.0089
Max Act: 7.0089. Min Act: -0.1700
Data Index: 988803 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.9152. Min Act: -0.1700
Data Index: 8497802 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8839. Min Act: -0.1700
Data Index: 3106336 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8839. Min Act: -0.1700
Data Index: 1757872 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8839. Min Act: -0.1700
Data Index: 1260624 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8527. Min Act: -0.1700
Data Index: 4578953 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8527. Min Act: -0.1700
Data Index: 4706392 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8214. Min Act: -0.1700
Data Index: 6667370 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8214. Min Act: -0.1700
Data Index: 8613982 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.8214. Min Act: -0.1700
Data Index: 2281918 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7902. Min Act: -0.1700
Data Index: 7882016 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7902. Min Act: -0.1700
Data Index: 4135933 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7902. Min Act: -0.1700
Data Index: 8767038 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7589. Min Act: -0.1700
Data Index: 3926453 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7589. Min Act: -0.1700
Data Index: 4240840 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7589. Min Act: -0.1700
Data Index: 3035438 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7277. Min Act: -0.1700
Data Index: 606590 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7589. Min Act: -0.1700
Data Index: 7766782 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.6964. Min Act: -0.1700
Data Index: 6220113 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0089. Min Range: -7.0089
Max Act: 6.7277. Min Act: -0.1700
Data Index: 6711453 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19