Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.7255. Min Act: -0.1700
Data Index: 3640958 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.5067. Min Act: -0.1700
Data Index: 1275684 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.3817. Min Act: -0.1700
Data Index: 7885847 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.3192. Min Act: -0.1700
Data Index: 2486220 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2880. Min Act: -0.1700
Data Index: 63619 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2567. Min Act: -0.1700
Data Index: 7279213 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2567. Min Act: -0.1700
Data Index: 7772118 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 8663126 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 5687111 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 8348248 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 8297405 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 8073077 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.1942. Min Act: -0.1700
Data Index: 4248377 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 7732755 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 259458 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.1942. Min Act: -0.1700
Data Index: 3475285 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.1942. Min Act: -0.1700
Data Index: 3416860 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.1942. Min Act: -0.1700
Data Index: 4244263 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.1942. Min Act: -0.1700
Data Index: 2710292 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7255. Min Range: -4.7255
Max Act: 4.2255. Min Act: -0.1700
Data Index: 6221319 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19