Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2161. Min Range: -5.2161
Max Act: 5.2161. Min Act: -0.1700
Data Index: 1404689 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2161. Min Range: -5.2161
Max Act: 5.0286. Min Act: -0.1700
Data Index: 1170895 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.9661. Min Act: -0.1700
Data Index: 7249681 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.9348. Min Act: -0.1700
Data Index: 6342366 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.9348. Min Act: -0.1700
Data Index: 3152001 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.9036. Min Act: -0.1700
Data Index: 462931 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.9036. Min Act: -0.1700
Data Index: 7186298 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8723. Min Act: -0.1700
Data Index: 2512145 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8411. Min Act: -0.1700
Data Index: 3809891 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8098. Min Act: -0.1700
Data Index: 1810350 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8411. Min Act: -0.1700
Data Index: 6818935 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8098. Min Act: -0.1700
Data Index: 171744 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8098. Min Act: -0.1700
Data Index: 4671502 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.7786. Min Act: -0.1700
Data Index: 1423948 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8098. Min Act: -0.1700
Data Index: 7039731 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.7786. Min Act: -0.1700
Data Index: 1869642 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8098. Min Act: -0.1700
Data Index: 7555613 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.8098. Min Act: -0.1700
Data Index: 5769934 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.7786. Min Act: -0.1700
Data Index: 1141514 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2161. Min Range: -5.2161
Max Act: 4.7161. Min Act: -0.1700
Data Index: 3594147 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19