Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.6509. Min Act: -0.1700
Data Index: 5742954 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.2759. Min Act: -0.1700
Data Index: 7812899 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.2447. Min Act: -0.1700
Data Index: 4032266 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.2134. Min Act: -0.1700
Data Index: 6521633 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.1509. Min Act: -0.1700
Data Index: 3121194 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.1509. Min Act: -0.1700
Data Index: 5742955 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.1197. Min Act: -0.1700
Data Index: 5064246 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.1197. Min Act: -0.1700
Data Index: 8389664 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0884. Min Act: -0.1700
Data Index: 6808203 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0884. Min Act: -0.1700
Data Index: 8502070 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0572. Min Act: -0.1700
Data Index: 2585115 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0572. Min Act: -0.1700
Data Index: 4253684 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0572. Min Act: -0.1700
Data Index: 5006766 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0259. Min Act: -0.1700
Data Index: 3313515 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0259. Min Act: -0.1700
Data Index: 6854942 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0259. Min Act: -0.1700
Data Index: 2255682 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0259. Min Act: -0.1700
Data Index: 156851 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0259. Min Act: -0.1700
Data Index: 4195774 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6509. Min Range: -6.6509
Max Act: 6.0259. Min Act: -0.1700
Data Index: 2329114 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6509. Min Range: -6.6509
Max Act: 5.9322. Min Act: -0.1700
Data Index: 5181135 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19