Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2276 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.3046. Min Act: -0.1700
Data Index: 5404930 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1796. Min Act: -0.1700
Data Index: 4137027 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1483. Min Act: -0.1700
Data Index: 7380739 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1483. Min Act: -0.1700
Data Index: 3543186 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1171. Min Act: -0.1700
Data Index: 7877754 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0858. Min Act: -0.1700
Data Index: 4915213 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0546. Min Act: -0.1700
Data Index: 5654140 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 5977459 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 640913 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 7913157 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 281656 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 4200100 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 4298376 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 793625 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 5615193 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9921. Min Act: -0.1700
Data Index: 6191284 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9608. Min Act: -0.1700
Data Index: 7465396 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9921. Min Act: -0.1700
Data Index: 2558759 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9608. Min Act: -0.1700
Data Index: 7266721 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9608. Min Act: -0.1700
Data Index: 4429740 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19