Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1541 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.3685. Min Act: -0.1700
Data Index: 8507355 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.4310. Min Act: -0.1700
Data Index: 6209006 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.2435. Min Act: -0.1700
Data Index: 1334611 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.2435. Min Act: -0.1700
Data Index: 8126702 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.2122. Min Act: -0.1700
Data Index: 1122600 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0560. Min Act: -0.1700
Data Index: 2977898 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0247. Min Act: -0.1700
Data Index: 3983253 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.9935. Min Act: -0.1700
Data Index: 4283646 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.9622. Min Act: -0.1700
Data Index: 3489279 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.9622. Min Act: -0.1700
Data Index: 7054453 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8997. Min Act: -0.1700
Data Index: 6398124 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8685. Min Act: -0.1700
Data Index: 3832364 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8997. Min Act: -0.1700
Data Index: 5223446 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8685. Min Act: -0.1700
Data Index: 6342332 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8685. Min Act: -0.1700
Data Index: 5145268 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8685. Min Act: -0.1700
Data Index: 3995140 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8685. Min Act: -0.1700
Data Index: 8710826 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.7747. Min Act: -0.1700
Data Index: 364286 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8060. Min Act: -0.1700
Data Index: 8595219 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.8060. Min Act: -0.1700
Data Index: 1335467 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19