Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2731 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.2669. Min Act: -0.1700
Data Index: 4212356 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.2356. Min Act: -0.1700
Data Index: 7878138 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.2669. Min Act: -0.1700
Data Index: 1136890 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 8372918 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 4294279 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 6252053 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 1519006 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.1419. Min Act: -0.1700
Data Index: 2842634 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.1106. Min Act: -0.1700
Data Index: 4312136 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.1106. Min Act: -0.1700
Data Index: 7669076 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.0481. Min Act: -0.1700
Data Index: 1168391 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.0481. Min Act: -0.1700
Data Index: 4125701 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.0481. Min Act: -0.1700
Data Index: 4683759 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.0169. Min Act: -0.1700
Data Index: 1517393 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2669. Min Range: -7.2669
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7755569 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2669. Min Range: -7.2669
Max Act: 6.9544. Min Act: -0.1700
Data Index: 3804672 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2669. Min Range: -7.2669
Max Act: 6.9544. Min Act: -0.1700
Data Index: 2319141 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2669. Min Range: -7.2669
Max Act: 6.9544. Min Act: -0.1700
Data Index: 5832043 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2669. Min Range: -7.2669
Max Act: 6.9544. Min Act: -0.1700
Data Index: 5589822 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2669. Min Range: -7.2669
Max Act: 6.9544. Min Act: -0.1700
Data Index: 3406127 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19