Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2140 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6893. Min Act: -0.1700
Data Index: 8234790 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.7206. Min Act: -0.1700
Data Index: 8091563 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6893. Min Act: -0.1700
Data Index: 3908916 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6580. Min Act: -0.1700
Data Index: 6748274 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6580. Min Act: -0.1700
Data Index: 1458256 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6580. Min Act: -0.1700
Data Index: 3432901 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6580. Min Act: -0.1700
Data Index: 8306734 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6580. Min Act: -0.1700
Data Index: 3797852 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 3533175 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 6512535 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 1047876 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 6485700 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 6748275 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 6900200 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 5324235 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 1427481 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 5325502 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 783965 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 7030578 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7206. Min Range: -3.7206
Max Act: 3.6267. Min Act: -0.1700
Data Index: 6220757 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19