Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.6480. Min Act: -0.1700
Data Index: 770084 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.6654. Min Act: -0.1700
Data Index: 1339246 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.6306. Min Act: -0.1700
Data Index: 1016178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5957. Min Act: -0.1700
Data Index: 2325949 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5782. Min Act: -0.1700
Data Index: 8014658 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5607. Min Act: -0.1700
Data Index: 691006 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5607. Min Act: -0.1700
Data Index: 6409182 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5607. Min Act: -0.1700
Data Index: 2427187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5432. Min Act: -0.1700
Data Index: 2264056 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5432. Min Act: -0.1700
Data Index: 186405 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5432. Min Act: -0.1700
Data Index: 3212423 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5257. Min Act: -0.1700
Data Index: 1232547 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5081. Min Act: -0.1700
Data Index: 1832871 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5257. Min Act: -0.1700
Data Index: 7893293 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5257. Min Act: -0.1700
Data Index: 2611388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5257. Min Act: -0.1700
Data Index: 7053235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5081. Min Act: -0.1700
Data Index: 5130805 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5257. Min Act: -0.1700
Data Index: 1677885 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5081. Min Act: -0.1700
Data Index: 2626154 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6654. Min Range: -1.6654
Max Act: 1.5081. Min Act: -0.1700
Data Index: 1385824 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19