Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.7591. Min Act: -0.1700
Data Index: 908846 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.4466. Min Act: -0.1700
Data Index: 3046583 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.3841. Min Act: -0.1700
Data Index: 2113459 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.3841. Min Act: -0.1700
Data Index: 6653085 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2903. Min Act: -0.1700
Data Index: 8374163 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2903. Min Act: -0.1700
Data Index: 6580159 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2903. Min Act: -0.1700
Data Index: 5778093 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2591. Min Act: -0.1700
Data Index: 3590979 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2278. Min Act: -0.1700
Data Index: 8252509 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2278. Min Act: -0.1700
Data Index: 4640452 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2278. Min Act: -0.1700
Data Index: 298680 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2597088 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2864147 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.1653. Min Act: -0.1700
Data Index: 1321354 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.1653. Min Act: -0.1700
Data Index: 8253213 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.1341. Min Act: -0.1700
Data Index: 3202950 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.1028. Min Act: -0.1700
Data Index: 7830286 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.1341. Min Act: -0.1700
Data Index: 7931282 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.0716. Min Act: -0.1700
Data Index: 2084668 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.1028. Min Act: -0.1700
Data Index: 687260 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19