Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0956. Min Act: -0.1234
Data Index: 4159032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0788. Min Act: -0.1694
Data Index: 4159036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0788. Min Act: -0.1700
Data Index: 2751866 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0620. Min Act: -0.1700
Data Index: 2737289 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0620. Min Act: -0.1700
Data Index: 7786769 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0620. Min Act: -0.1700
Data Index: 2378467 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0452. Min Act: -0.1700
Data Index: 3244664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0452. Min Act: -0.1700
Data Index: 941932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0452. Min Act: -0.1700
Data Index: 4179746 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0284. Min Act: -0.1700
Data Index: 3764781 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0284. Min Act: -0.1700
Data Index: 2301784 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0115. Min Act: -0.1700
Data Index: 7948280 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0115. Min Act: -0.1700
Data Index: 8293423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0956. Min Range: -2.0956
Max Act: 2.0115. Min Act: -0.1700
Data Index: 4498337 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0956. Min Range: -2.0956
Max Act: 1.9946. Min Act: -0.1700
Data Index: 2097840 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0956. Min Range: -2.0956
Max Act: 1.9946. Min Act: -0.1698
Data Index: 3371642 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0956. Min Range: -2.0956
Max Act: 1.9946. Min Act: -0.1662
Data Index: 4159002 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0956. Min Range: -2.0956
Max Act: 1.9777. Min Act: -0.1697
Data Index: 4159010 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0956. Min Range: -2.0956
Max Act: 1.9946. Min Act: -0.1700
Data Index: 179467 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0956. Min Range: -2.0956
Max Act: 1.9777. Min Act: -0.1700
Data Index: 4754986 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19