Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5749. Min Act: -0.1700
Data Index: 1814360 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5124. Min Act: -0.1700
Data Index: 6638827 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5436. Min Act: -0.1700
Data Index: 3912554 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5436. Min Act: -0.1700
Data Index: 4037171 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4811. Min Act: -0.1700
Data Index: 4532297 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4499. Min Act: -0.1700
Data Index: 5077451 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4499. Min Act: -0.1700
Data Index: 4800671 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4186. Min Act: -0.1700
Data Index: 2451711 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3874. Min Act: -0.1700
Data Index: 8539723 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4499. Min Act: -0.1700
Data Index: 8764828 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3874. Min Act: -0.1700
Data Index: 3943736 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 7620440 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 334352 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3561. Min Act: -0.1700
Data Index: 5300237 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 6098418 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 6780791 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 6344073 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3249. Min Act: -0.1700
Data Index: 1991303 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2936. Min Act: -0.1700
Data Index: 181339 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2936. Min Act: -0.1700
Data Index: 4416455 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19