Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 619 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0247. Min Range: -6.0247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 7169256 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0247. Min Range: -6.0247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 756462 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8684. Min Act: -0.1700
Data Index: 7004216 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8372. Min Act: -0.1700
Data Index: 5579747 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8059. Min Act: -0.1700
Data Index: 3225214 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8059. Min Act: -0.1700
Data Index: 10267 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.6497. Min Act: -0.1700
Data Index: 3174375 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.6184. Min Act: -0.1700
Data Index: 1841859 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.6497. Min Act: -0.1700
Data Index: 6245949 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.6184. Min Act: -0.1700
Data Index: 3917843 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5872. Min Act: -0.1700
Data Index: 4055153 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.6184. Min Act: -0.1700
Data Index: 8126944 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.6184. Min Act: -0.1700
Data Index: 5909992 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5872. Min Act: -0.1700
Data Index: 4648924 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5872. Min Act: -0.1700
Data Index: 1223428 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5872. Min Act: -0.1700
Data Index: 2628256 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5559. Min Act: -0.1700
Data Index: 3180531 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5247. Min Act: -0.1700
Data Index: 3281268 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5559. Min Act: -0.1700
Data Index: 4747245 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.5559. Min Act: -0.1700
Data Index: 3750383 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19