Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1579 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.4495. Min Act: -0.1700
Data Index: 93431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.3245. Min Act: -0.1700
Data Index: 93419 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.3245. Min Act: -0.1700
Data Index: 93435 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.3557. Min Act: -0.1700
Data Index: 93415 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2932. Min Act: -0.1700
Data Index: 93417 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2932. Min Act: -0.1700
Data Index: 7678628 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2620. Min Act: -0.1700
Data Index: 93404 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2620. Min Act: -0.1700
Data Index: 93393 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2620. Min Act: -0.1700
Data Index: 93395 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2620. Min Act: -0.1700
Data Index: 93391 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2932. Min Act: -0.1700
Data Index: 3351845 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2307. Min Act: -0.1700
Data Index: 93434 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.1995. Min Act: -0.1700
Data Index: 93390 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2307. Min Act: -0.1700
Data Index: 93430 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2307. Min Act: -0.1700
Data Index: 2002873 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2307. Min Act: -0.1700
Data Index: 5265091 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2307. Min Act: -0.1700
Data Index: 93432 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.2307. Min Act: -0.1700
Data Index: 4182874 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.1995. Min Act: -0.1700
Data Index: 994833 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4495. Min Range: -5.4495
Max Act: 5.1995. Min Act: -0.1700
Data Index: 93389 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19