Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.7568. Min Act: -0.1700
Data Index: 6066968 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.4443. Min Act: -0.1700
Data Index: 7171821 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.3818. Min Act: -0.1700
Data Index: 3213581 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.2568. Min Act: -0.1700
Data Index: 2091212 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.1943. Min Act: -0.1700
Data Index: 3304185 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.1318. Min Act: -0.1700
Data Index: 425386 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.1318. Min Act: -0.1700
Data Index: 3551928 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.1318. Min Act: -0.1700
Data Index: 750459 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.1318. Min Act: -0.1700
Data Index: 1442407 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.0693. Min Act: -0.1700
Data Index: 470238 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.0068. Min Act: -0.1700
Data Index: 8313776 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.0068. Min Act: -0.1700
Data Index: 3969603 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7568. Min Range: -9.7568
Max Act: 8.9443. Min Act: -0.1700
Data Index: 3356144 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7568. Min Range: -9.7568
Max Act: 9.0068. Min Act: -0.1700
Data Index: 7803253 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7568. Min Range: -9.7568
Max Act: 8.9443. Min Act: -0.1700
Data Index: 2524378 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7568. Min Range: -9.7568
Max Act: 8.9443. Min Act: -0.1700
Data Index: 3375623 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7568. Min Range: -9.7568
Max Act: 8.9443. Min Act: -0.1700
Data Index: 7380474 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7568. Min Range: -9.7568
Max Act: 8.9443. Min Act: -0.1700
Data Index: 1028778 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7568. Min Range: -9.7568
Max Act: 8.9443. Min Act: -0.1700
Data Index: 2688161 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7568. Min Range: -9.7568
Max Act: 8.9443. Min Act: -0.1700
Data Index: 3974181 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19