Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1312. Min Range: -7.1312
Max Act: 7.1312. Min Act: -0.1700
Data Index: 5217438 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1312. Min Range: -7.1312
Max Act: 7.0062. Min Act: -0.1700
Data Index: 6825319 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.8812. Min Act: -0.1700
Data Index: 526588 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.8187. Min Act: -0.1700
Data Index: 1639443 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.7874. Min Act: -0.1700
Data Index: 6499373 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.7562. Min Act: -0.1700
Data Index: 6391760 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.7562. Min Act: -0.1700
Data Index: 1045680 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.6937. Min Act: -0.1700
Data Index: 7670098 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.6937. Min Act: -0.1700
Data Index: 692670 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.6624. Min Act: -0.1700
Data Index: 743865 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.6312. Min Act: -0.1700
Data Index: 4858620 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.6312. Min Act: -0.1700
Data Index: 1470641 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.5999. Min Act: -0.1700
Data Index: 1009917 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.5999. Min Act: -0.1700
Data Index: 1988774 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.5999. Min Act: -0.1700
Data Index: 2487207 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.5687. Min Act: -0.1700
Data Index: 3330836 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.5687. Min Act: -0.1700
Data Index: 6164083 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.5374. Min Act: -0.1700
Data Index: 4391543 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.4749. Min Act: -0.1700
Data Index: 1561214 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1312. Min Range: -7.1312
Max Act: 6.5062. Min Act: -0.1700
Data Index: 4109048 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19