Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2312 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.4793. Min Act: -0.1700
Data Index: 2860852 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.4481. Min Act: -0.1700
Data Index: 8627274 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.3543. Min Act: -0.1700
Data Index: 7001811 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.3543. Min Act: -0.1700
Data Index: 6338693 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.3231. Min Act: -0.1700
Data Index: 8491236 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3316329 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.3231. Min Act: -0.1700
Data Index: 5705100 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2606. Min Act: -0.1700
Data Index: 4552861 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2606. Min Act: -0.1700
Data Index: 2523670 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2293. Min Act: -0.1700
Data Index: 8086089 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2293. Min Act: -0.1700
Data Index: 2623974 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2293. Min Act: -0.1700
Data Index: 8308416 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1981. Min Act: -0.1700
Data Index: 6887368 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2293. Min Act: -0.1700
Data Index: 1064810 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1981. Min Act: -0.1700
Data Index: 4531373 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1981. Min Act: -0.1700
Data Index: 2792942 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1981. Min Act: -0.1700
Data Index: 6185348 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1981. Min Act: -0.1700
Data Index: 6721439 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1981. Min Act: -0.1700
Data Index: 375039 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1356. Min Act: -0.1700
Data Index: 1143722 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19