Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.2494. Min Act: -0.1700
Data Index: 7829835 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.2163. Min Act: -0.1700
Data Index: 161183 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1831. Min Act: -0.1700
Data Index: 4550567 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1831. Min Act: -0.1700
Data Index: 1450076 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1831. Min Act: -0.1697
Data Index: 7364249 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1665. Min Act: -0.1700
Data Index: 1024996 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1665. Min Act: -0.1700
Data Index: 5964249 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1665. Min Act: -0.1700
Data Index: 7494293 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1332. Min Act: -0.1700
Data Index: 2804375 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1498. Min Act: -0.1700
Data Index: 6400950 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1332. Min Act: -0.1700
Data Index: 5793382 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1332. Min Act: -0.1700
Data Index: 2438905 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1332. Min Act: -0.1700
Data Index: 3838935 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1332. Min Act: -0.1700
Data Index: 3031463 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0997. Min Act: -0.1700
Data Index: 5361370 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1165. Min Act: -0.1700
Data Index: 6130308 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1165. Min Act: -0.1700
Data Index: 2523336 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0997. Min Act: -0.1700
Data Index: 8252907 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1165. Min Act: -0.1700
Data Index: 6558720 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1165. Min Act: -0.1700
Data Index: 3107861 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19