Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8869. Min Act: -0.1700
Data Index: 474707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8869. Min Act: -0.1700
Data Index: 1738811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8869. Min Act: -0.1700
Data Index: 525108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8557. Min Act: -0.1700
Data Index: 8286662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8557. Min Act: -0.1700
Data Index: 1309628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8557. Min Act: -0.1700
Data Index: 8758174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 8435339 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 3932039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 1306515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 340057 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 7784699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 4509758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 2204824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7932. Min Act: -0.1700
Data Index: 1754716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7932. Min Act: -0.1700
Data Index: 3236217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7932. Min Act: -0.1700
Data Index: 183918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7932. Min Act: -0.1700
Data Index: 5252994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 6362763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7932. Min Act: -0.1700
Data Index: 537530 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7932. Min Act: -0.1700
Data Index: 6397265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19