Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.3939. Min Act: -0.1700
Data Index: 2448795 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.3314. Min Act: -0.1700
Data Index: 18653 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.3002. Min Act: -0.1700
Data Index: 3540748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.3002. Min Act: -0.1700
Data Index: 3045958 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.3002. Min Act: -0.1700
Data Index: 7894787 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2689. Min Act: -0.1700
Data Index: 1012141 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6984224 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2064. Min Act: -0.1700
Data Index: 4621144 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2064. Min Act: -0.1699
Data Index: 8383643 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2064. Min Act: -0.1700
Data Index: 1486277 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2377. Min Act: -0.1700
Data Index: 2357693 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2064. Min Act: -0.1700
Data Index: 5097227 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.2377. Min Act: -0.1700
Data Index: 7331901 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.1752. Min Act: -0.1700
Data Index: 368814 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.1752. Min Act: -0.1700
Data Index: 7549103 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.1752. Min Act: -0.1699
Data Index: 3940277 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.1752. Min Act: -0.1700
Data Index: 263739 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.1439. Min Act: -0.1700
Data Index: 3789178 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.1439. Min Act: -0.1700
Data Index: 363408 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3939. Min Range: -5.3939
Max Act: 5.1439. Min Act: -0.1700
Data Index: 2561475 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19