Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1600 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7089. Min Range: -8.7089
Max Act: 8.7089. Min Act: -0.1700
Data Index: 5288869 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.8964. Min Act: -0.1700
Data Index: 39199 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.8027. Min Act: -0.1700
Data Index: 701955 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.6777. Min Act: -0.1700
Data Index: 1154146 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.7714. Min Act: -0.1700
Data Index: 1262454 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.6777. Min Act: -0.1700
Data Index: 776102 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.6464. Min Act: -0.1700
Data Index: 1361625 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.6464. Min Act: -0.1700
Data Index: 4023197 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.6464. Min Act: -0.1700
Data Index: 1667304 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.5839. Min Act: -0.1700
Data Index: 8060749 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.6152. Min Act: -0.1700
Data Index: 7656798 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.5527. Min Act: -0.1700
Data Index: 3509412 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.5214. Min Act: -0.1700
Data Index: 8457813 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.4277. Min Act: -0.1700
Data Index: 2776438 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.4277. Min Act: -0.1700
Data Index: 5824848 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.4902. Min Act: -0.1700
Data Index: 168029 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.4277. Min Act: -0.1700
Data Index: 2306786 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.4277. Min Act: -0.1700
Data Index: 4511064 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.4277. Min Act: -0.1700
Data Index: 806245 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7089. Min Range: -8.7089
Max Act: 7.4589. Min Act: -0.1700
Data Index: 769066 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19