Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.4949. Min Act: -0.1700
Data Index: 5334306 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.4011. Min Act: -0.1700
Data Index: 5964463 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.4011. Min Act: -0.1700
Data Index: 5601879 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3698. Min Act: -0.1700
Data Index: 1559015 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3698. Min Act: -0.1700
Data Index: 2100956 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3698. Min Act: -0.1700
Data Index: 3177137 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3386. Min Act: -0.1700
Data Index: 1989836 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3073. Min Act: -0.1700
Data Index: 3158481 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3386. Min Act: -0.1700
Data Index: 6984329 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3386. Min Act: -0.1700
Data Index: 6369515 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3073. Min Act: -0.1700
Data Index: 3009497 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3386. Min Act: -0.1700
Data Index: 3931481 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3386. Min Act: -0.1700
Data Index: 2752988 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3386. Min Act: -0.1700
Data Index: 1022506 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3073. Min Act: -0.1700
Data Index: 1024008 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3073. Min Act: -0.1700
Data Index: 3085010 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.2761. Min Act: -0.1700
Data Index: 3238093 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3073. Min Act: -0.1700
Data Index: 149287 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3073. Min Act: -0.1700
Data Index: 1056535 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.3073. Min Act: -0.1700
Data Index: 2100959 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19