Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4643 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3163. Min Range: -6.3163
Max Act: 6.3163. Min Act: -0.1700
Data Index: 7798087 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3163. Min Range: -6.3163
Max Act: 6.1288. Min Act: -0.1700
Data Index: 2020033 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3163. Min Range: -6.3163
Max Act: 6.0976. Min Act: -0.1700
Data Index: 3537049 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3163. Min Range: -6.3163
Max Act: 6.0976. Min Act: -0.1700
Data Index: 1937136 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3163. Min Range: -6.3163
Max Act: 6.0663. Min Act: -0.1700
Data Index: 3337462 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.9726. Min Act: -0.1700
Data Index: 571096 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.8788. Min Act: -0.1700
Data Index: 7804973 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.8163. Min Act: -0.1700
Data Index: 8609466 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.8163. Min Act: -0.1700
Data Index: 2031435 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6856473 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.7851. Min Act: -0.1700
Data Index: 7003294 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1476591 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.7538. Min Act: -0.1700
Data Index: 170431 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.6913. Min Act: -0.1700
Data Index: 6189957 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.6913. Min Act: -0.1700
Data Index: 978953 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.6913. Min Act: -0.1700
Data Index: 6725047 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.6601. Min Act: -0.1700
Data Index: 278990 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.6288. Min Act: -0.1700
Data Index: 8720057 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.6601. Min Act: -0.1700
Data Index: 2319441 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3163. Min Range: -6.3163
Max Act: 5.6288. Min Act: -0.1700
Data Index: 2827347 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19