Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.9702. Min Act: -0.1700
Data Index: 4502546 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.9077. Min Act: -0.1700
Data Index: 4099638 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5952. Min Act: -0.1700
Data Index: 1370901 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5640. Min Act: -0.1700
Data Index: 8145175 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5327. Min Act: -0.1700
Data Index: 4454710 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5015. Min Act: -0.1700
Data Index: 6621056 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5015. Min Act: -0.1700
Data Index: 2885954 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5640. Min Act: -0.1700
Data Index: 504383 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5015. Min Act: -0.1700
Data Index: 6794614 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.5015. Min Act: -0.1700
Data Index: 2106482 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.3765. Min Act: -0.1700
Data Index: 3148288 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.3765. Min Act: -0.1700
Data Index: 7850574 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.3140. Min Act: -0.1700
Data Index: 2933859 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.3452. Min Act: -0.1700
Data Index: 7788465 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.3140. Min Act: -0.1700
Data Index: 44421 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 111539 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.2202. Min Act: -0.1700
Data Index: 7252007 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.2202. Min Act: -0.1700
Data Index: 435212 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.1890. Min Act: -0.1700
Data Index: 7610179 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9702. Min Range: -5.9702
Max Act: 5.2202. Min Act: -0.1700
Data Index: 4045865 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19