Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4966 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.2893. Min Act: -0.1700
Data Index: 7415482 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.2893. Min Act: -0.1700
Data Index: 3883222 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.2580. Min Act: -0.1700
Data Index: 696675 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.1955. Min Act: -0.1700
Data Index: 6430521 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.1643. Min Act: -0.1700
Data Index: 4688867 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.1018. Min Act: -0.1700
Data Index: 1221660 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.1018. Min Act: -0.1700
Data Index: 4272779 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0393. Min Act: -0.1700
Data Index: 402729 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0705. Min Act: -0.1700
Data Index: 675661 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0393. Min Act: -0.1700
Data Index: 8255808 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0705. Min Act: -0.1700
Data Index: 1487729 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0393. Min Act: -0.1700
Data Index: 8350860 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0080. Min Act: -0.1700
Data Index: 3725202 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2893. Min Range: -5.2893
Max Act: 4.9768. Min Act: -0.1700
Data Index: 325187 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0080. Min Act: -0.1700
Data Index: 5654335 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2893. Min Range: -5.2893
Max Act: 5.0080. Min Act: -0.1700
Data Index: 874510 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2893. Min Range: -5.2893
Max Act: 4.9455. Min Act: -0.1700
Data Index: 2548574 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2893. Min Range: -5.2893
Max Act: 4.9455. Min Act: -0.1700
Data Index: 5681319 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2893. Min Range: -5.2893
Max Act: 4.9143. Min Act: -0.1700
Data Index: 2248216 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2893. Min Range: -5.2893
Max Act: 4.8830. Min Act: -0.1700
Data Index: 2368662 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19