Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1855 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.5093. Min Act: -0.1700
Data Index: 1133620 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.3531. Min Act: -0.1700
Data Index: 6962781 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.3531. Min Act: -0.1700
Data Index: 979399 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.3218. Min Act: -0.1700
Data Index: 4540036 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.3218. Min Act: -0.1700
Data Index: 5373132 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.2906. Min Act: -0.1700
Data Index: 18271 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.2593. Min Act: -0.1700
Data Index: 6962783 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.2593. Min Act: -0.1700
Data Index: 1133619 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.2593. Min Act: -0.1700
Data Index: 8126433 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.2281. Min Act: -0.1700
Data Index: 1617106 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1968. Min Act: -0.1700
Data Index: 3009250 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1968. Min Act: -0.1700
Data Index: 6137981 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1968. Min Act: -0.1700
Data Index: 4134382 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1656. Min Act: -0.1700
Data Index: 6515432 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1656. Min Act: -0.1700
Data Index: 4540035 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1656. Min Act: -0.1700
Data Index: 5167401 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1656. Min Act: -0.1700
Data Index: 1600794 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1031. Min Act: -0.1700
Data Index: 2622645 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1031. Min Act: -0.1700
Data Index: 3781342 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5093. Min Range: -5.5093
Max Act: 5.1031. Min Act: -0.1700
Data Index: 6137983 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19