Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 42 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2161. Min Range: -6.2161
Max Act: 6.2161. Min Act: -0.1700
Data Index: 3788108 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2161. Min Range: -6.2161
Max Act: 6.1848. Min Act: -0.1700
Data Index: 6408143 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2161. Min Range: -6.2161
Max Act: 6.1536. Min Act: -0.1700
Data Index: 2419038 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2161. Min Range: -6.2161
Max Act: 6.0598. Min Act: -0.1700
Data Index: 4409119 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2161. Min Range: -6.2161
Max Act: 6.0598. Min Act: -0.1700
Data Index: 2247754 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9661. Min Act: -0.1700
Data Index: 8155378 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9348. Min Act: -0.1700
Data Index: 3623614 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9036. Min Act: -0.1700
Data Index: 2368534 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9348. Min Act: -0.1700
Data Index: 4386323 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9036. Min Act: -0.1700
Data Index: 6753044 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9036. Min Act: -0.1700
Data Index: 1773550 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9036. Min Act: -0.1700
Data Index: 8407380 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8723. Min Act: -0.1700
Data Index: 3864276 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8723. Min Act: -0.1700
Data Index: 8387039 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8411. Min Act: -0.1700
Data Index: 6284161 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8723. Min Act: -0.1700
Data Index: 6422362 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8098. Min Act: -0.1700
Data Index: 7801728 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.7473. Min Act: -0.1700
Data Index: 85860 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.7786. Min Act: -0.1700
Data Index: 6610615 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.7786. Min Act: -0.1700
Data Index: 5279197 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19