Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.2776. Min Act: -0.1700
Data Index: 2299014 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.2151. Min Act: -0.1700
Data Index: 731465 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.1839. Min Act: -0.1700
Data Index: 8322818 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.1214. Min Act: -0.1700
Data Index: 7910905 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1582405 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.1214. Min Act: -0.1700
Data Index: 7047164 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0901. Min Act: -0.1700
Data Index: 3155106 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0901. Min Act: -0.1700
Data Index: 3278210 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0276. Min Act: -0.1700
Data Index: 6607464 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9651. Min Act: -0.1700
Data Index: 8532904 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9651. Min Act: -0.1700
Data Index: 6115034 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0276. Min Act: -0.1700
Data Index: 639081 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9964. Min Act: -0.1700
Data Index: 4172370 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4465424 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9339. Min Act: -0.1700
Data Index: 7760948 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9026. Min Act: -0.1700
Data Index: 184857 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.8714. Min Act: -0.1700
Data Index: 3771960 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.8714. Min Act: -0.1700
Data Index: 2995951 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5923394 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9026. Min Act: -0.1700
Data Index: 3985581 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19