Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3774 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.4669. Min Act: -0.1700
Data Index: 3271981 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.3107. Min Act: -0.1700
Data Index: 79503 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.3419. Min Act: -0.1700
Data Index: 1322896 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.1857. Min Act: -0.1700
Data Index: 8231207 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.1232. Min Act: -0.1700
Data Index: 329419 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.0919. Min Act: -0.1700
Data Index: 412507 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.0607. Min Act: -0.1700
Data Index: 7218823 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4669. Min Range: -6.4669
Max Act: 6.0607. Min Act: -0.1700
Data Index: 3599594 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9982. Min Act: -0.1700
Data Index: 841317 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9982. Min Act: -0.1700
Data Index: 5902635 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9669. Min Act: -0.1700
Data Index: 8502443 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9669. Min Act: -0.1700
Data Index: 3331059 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9669. Min Act: -0.1700
Data Index: 1263262 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9357. Min Act: -0.1700
Data Index: 5921980 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9044. Min Act: -0.1700
Data Index: 549811 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9357. Min Act: -0.1700
Data Index: 1698128 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9357. Min Act: -0.1700
Data Index: 298193 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9044. Min Act: -0.1700
Data Index: 1342673 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9357. Min Act: -0.1700
Data Index: 2971326 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4669. Min Range: -6.4669
Max Act: 5.9044. Min Act: -0.1700
Data Index: 6851253 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19