Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 918 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.5545. Min Act: -0.1700
Data Index: 3431505 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.4295. Min Act: -0.1700
Data Index: 4958973 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.4920. Min Act: -0.1700
Data Index: 2439517 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.3670. Min Act: -0.1700
Data Index: 3714120 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.3670. Min Act: -0.1700
Data Index: 7397897 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.3045. Min Act: -0.1700
Data Index: 8762242 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.2420. Min Act: -0.1700
Data Index: 8451155 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.3045. Min Act: -0.1700
Data Index: 7842378 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.3045. Min Act: -0.1700
Data Index: 6862428 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.3045. Min Act: -0.1700
Data Index: 2125430 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.2420. Min Act: -0.1700
Data Index: 109471 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.2420. Min Act: -0.1700
Data Index: 1498607 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.2420. Min Act: -0.1700
Data Index: 6449676 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.2420. Min Act: -0.1700
Data Index: 4085193 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.2420. Min Act: -0.1700
Data Index: 5456679 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.2420. Min Act: -0.1700
Data Index: 4311533 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.1795. Min Act: -0.1700
Data Index: 1212224 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.1795. Min Act: -0.1700
Data Index: 7848253 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.1795. Min Act: -0.1700
Data Index: 8108385 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5545. Min Range: -8.5545
Max Act: 8.1795. Min Act: -0.1700
Data Index: 1204822 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19