Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.4942. Min Act: -0.1700
Data Index: 7820564 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.4062. Min Act: -0.1700
Data Index: 5161071 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.3534. Min Act: -0.1700
Data Index: 4375168 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.3445. Min Act: -0.1700
Data Index: 5699753 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.3445. Min Act: -0.1700
Data Index: 2551200 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.3534. Min Act: -0.1700
Data Index: 1160135 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.3357. Min Act: -0.1700
Data Index: 5161072 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.3181. Min Act: -0.1700
Data Index: 720291 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.3093. Min Act: -0.1700
Data Index: 1434653 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2740. Min Act: -0.1700
Data Index: 7508666 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2740. Min Act: -0.1700
Data Index: 7613031 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2652. Min Act: -0.1700
Data Index: 2053097 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2652. Min Act: -0.1700
Data Index: 8516933 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2652. Min Act: -0.1700
Data Index: 1007139 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2563. Min Act: -0.1700
Data Index: 5161073 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2652. Min Act: -0.1700
Data Index: 8622407 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2563. Min Act: -0.1700
Data Index: 6372074 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2563. Min Act: -0.1700
Data Index: 6005669 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2475. Min Act: -0.1700
Data Index: 1385805 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4942. Min Range: -1.4942
Max Act: 1.2387. Min Act: -0.1700
Data Index: 8270742 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19