Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.8436. Min Act: -0.1700
Data Index: 6333565 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.8123. Min Act: -0.1700
Data Index: 5757611 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.7811. Min Act: -0.1700
Data Index: 2155700 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.7811. Min Act: -0.1700
Data Index: 7965444 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.7811. Min Act: -0.1700
Data Index: 1550013 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.7498. Min Act: -0.1700
Data Index: 30238 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.7186. Min Act: -0.1700
Data Index: 4652008 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.7811. Min Act: -0.1700
Data Index: 3117420 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.6561. Min Act: -0.1700
Data Index: 4558878 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.6561. Min Act: -0.1700
Data Index: 1531083 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.6561. Min Act: -0.1700
Data Index: 6492933 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.6248. Min Act: -0.1700
Data Index: 7215029 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.5623. Min Act: -0.1700
Data Index: 2697026 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.5623. Min Act: -0.1700
Data Index: 8740526 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.5936. Min Act: -0.1700
Data Index: 7702699 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.5936. Min Act: -0.1700
Data Index: 8660804 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.5311. Min Act: -0.1700
Data Index: 3995949 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.5623. Min Act: -0.1700
Data Index: 2872237 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.5311. Min Act: -0.1700
Data Index: 6608738 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8436. Min Range: -5.8436
Max Act: 5.4998. Min Act: -0.1700
Data Index: 1130860 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19