Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 717 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.8163. Min Act: -0.1700
Data Index: 1360588 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.6288. Min Act: -0.1700
Data Index: 4263205 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.5976. Min Act: -0.1700
Data Index: 408203 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.5351. Min Act: -0.1700
Data Index: 2635400 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.5038. Min Act: -0.1700
Data Index: 5765751 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.4413. Min Act: -0.1700
Data Index: 5521182 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.4413. Min Act: -0.1700
Data Index: 1672799 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.3476. Min Act: -0.1700
Data Index: 4509944 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.3788. Min Act: -0.1700
Data Index: 2625845 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.3476. Min Act: -0.1700
Data Index: 4494143 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.3476. Min Act: -0.1700
Data Index: 7294794 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.2538. Min Act: -0.1700
Data Index: 1827860 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.2226. Min Act: -0.1700
Data Index: 925508 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.2226. Min Act: -0.1700
Data Index: 4375349 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.2226. Min Act: -0.1700
Data Index: 6386188 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.2226. Min Act: -0.1700
Data Index: 1513366 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.2226. Min Act: -0.1700
Data Index: 5504456 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.2226. Min Act: -0.1700
Data Index: 5452796 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.1913. Min Act: -0.1700
Data Index: 6386185 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8163. Min Range: -7.8163
Max Act: 7.1913. Min Act: -0.1700
Data Index: 1665218 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19