Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4469 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.1247. Min Act: -0.1700
Data Index: 8586785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0408. Min Act: -0.1700
Data Index: 5946861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0240. Min Act: -0.1700
Data Index: 1506459 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0240. Min Act: -0.1700
Data Index: 896357 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 3309586 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0240. Min Act: -0.1700
Data Index: 6551619 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0240. Min Act: -0.1700
Data Index: 7895051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0240. Min Act: -0.1700
Data Index: 8610952 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0240. Min Act: -0.1700
Data Index: 5193501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0240. Min Act: -0.1700
Data Index: 4154586 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 1274250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 4987350 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 4750516 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 2213036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 1194649 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 73737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 1172950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 4350353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 1596262 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1247. Min Range: -2.1247
Max Act: 2.0071. Min Act: -0.1700
Data Index: 1576722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19