Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.8045. Min Act: -0.1700
Data Index: 3616639 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.8045. Min Act: -0.1700
Data Index: 3815961 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.7107. Min Act: -0.1700
Data Index: 5884542 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.7420. Min Act: -0.1700
Data Index: 3311478 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.7420. Min Act: -0.1700
Data Index: 5481383 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2521633 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.6795. Min Act: -0.1700
Data Index: 2640727 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.6795. Min Act: -0.1700
Data Index: 4375117 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.6795. Min Act: -0.1700
Data Index: 3066273 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.6795. Min Act: -0.1700
Data Index: 1124712 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.6170. Min Act: -0.1700
Data Index: 6540857 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5857. Min Act: -0.1700
Data Index: 1247670 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5857. Min Act: -0.1700
Data Index: 8273681 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.6170. Min Act: -0.1700
Data Index: 2553095 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5857. Min Act: -0.1700
Data Index: 3930168 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5545. Min Act: -0.1700
Data Index: 6952659 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5545. Min Act: -0.1700
Data Index: 6609804 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5857. Min Act: -0.1700
Data Index: 6998594 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5857. Min Act: -0.1700
Data Index: 3327548 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8045. Min Range: -4.8045
Max Act: 4.5857. Min Act: -0.1700
Data Index: 1571814 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19