Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 480 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 5676231 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 4086735 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.5312. Min Act: -0.1700
Data Index: 2063714 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4374. Min Act: -0.1700
Data Index: 8742434 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4374. Min Act: -0.1700
Data Index: 561523 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.4062. Min Act: -0.1700
Data Index: 1628953 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3749. Min Act: -0.1700
Data Index: 1774736 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3749. Min Act: -0.1700
Data Index: 426447 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3749. Min Act: -0.1700
Data Index: 3534254 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3749. Min Act: -0.1700
Data Index: 3868369 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 2290059 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3437. Min Act: -0.1700
Data Index: 1981099 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3124. Min Act: -0.1700
Data Index: 3798481 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3124. Min Act: -0.1700
Data Index: 2126394 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.3124. Min Act: -0.1700
Data Index: 3273486 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2812. Min Act: -0.1700
Data Index: 7878352 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2812. Min Act: -0.1700
Data Index: 7597508 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2812. Min Act: -0.1700
Data Index: 3813648 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2812. Min Act: -0.1700
Data Index: 7371887 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5937. Min Range: -5.5937
Max Act: 5.2187. Min Act: -0.1700
Data Index: 2711755 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19