Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4592 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.4497. Min Act: -0.1700
Data Index: 2314345 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.4497. Min Act: -0.1700
Data Index: 2314344 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.4497. Min Act: -0.1700
Data Index: 6085218 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.3872. Min Act: -0.1700
Data Index: 2314341 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.3872. Min Act: -0.1700
Data Index: 2314343 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.3247. Min Act: -0.1700
Data Index: 2314342 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.2310. Min Act: -0.1700
Data Index: 4045183 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.2622. Min Act: -0.1700
Data Index: 4165877 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.1685. Min Act: -0.1700
Data Index: 861609 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.1685. Min Act: -0.1700
Data Index: 8268692 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.1997. Min Act: -0.1700
Data Index: 2847702 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.1060. Min Act: -0.1700
Data Index: 1243989 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.1060. Min Act: -0.1700
Data Index: 7688476 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.1060. Min Act: -0.1700
Data Index: 3134056 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.1060. Min Act: -0.1700
Data Index: 8229637 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.0747. Min Act: -0.1700
Data Index: 534754 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.0747. Min Act: -0.1700
Data Index: 5781125 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.0435. Min Act: -0.1700
Data Index: 1046037 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.0435. Min Act: -0.1700
Data Index: 1061071 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4497. Min Range: -5.4497
Max Act: 5.0435. Min Act: -0.1700
Data Index: 3313256 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19