Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 958 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.6635. Min Act: -0.1700
Data Index: 4911218 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.6635. Min Act: -0.1700
Data Index: 4733615 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.5697. Min Act: -0.1700
Data Index: 875255 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.5385. Min Act: -0.1700
Data Index: 2648950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4760. Min Act: -0.1700
Data Index: 3641905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.5072. Min Act: -0.1699
Data Index: 3005111 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4760. Min Act: -0.1693
Data Index: 1263351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4447. Min Act: -0.1694
Data Index: 6576408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4447. Min Act: -0.1700
Data Index: 4925400 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4135. Min Act: -0.1700
Data Index: 3487780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4760. Min Act: -0.1700
Data Index: 8069731 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4447. Min Act: -0.1700
Data Index: 1945712 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4447. Min Act: -0.1700
Data Index: 5296021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.3822. Min Act: -0.1700
Data Index: 4667041 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.3822. Min Act: -0.1700
Data Index: 4307028 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4135. Min Act: -0.1700
Data Index: 1137887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.3822. Min Act: -0.1700
Data Index: 1360290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4135. Min Act: -0.1700
Data Index: 5210092 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4135. Min Act: -0.1700
Data Index: 5219538 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6635. Min Range: -5.6635
Max Act: 5.4135. Min Act: -0.1700
Data Index: 5261522 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19