Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.3043. Min Act: -0.1700
Data Index: 410871 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2572. Min Act: -0.1700
Data Index: 3983607 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2415. Min Act: -0.1700
Data Index: 7485453 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2415. Min Act: -0.1700
Data Index: 2204841 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2415. Min Act: -0.1700
Data Index: 6506119 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2415. Min Act: -0.1700
Data Index: 119590 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2101. Min Act: -0.1700
Data Index: 2560249 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2258. Min Act: -0.1700
Data Index: 1025749 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2101. Min Act: -0.1700
Data Index: 3439527 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2101. Min Act: -0.1700
Data Index: 3528906 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.2101. Min Act: -0.1700
Data Index: 7611729 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 2603316 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 3018659 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 6495785 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 7553937 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 3537530 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 865301 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 6315752 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 2848471 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3043. Min Range: -3.3043
Max Act: 3.1944. Min Act: -0.1700
Data Index: 1068754 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19