Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4111 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.5980. Min Act: -0.1700
Data Index: 4045246 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.5668. Min Act: -0.1700
Data Index: 4663355 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.4730. Min Act: -0.1700
Data Index: 6171207 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.4730. Min Act: -0.1700
Data Index: 6182574 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.4730. Min Act: -0.1700
Data Index: 8148754 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.3793. Min Act: -0.1700
Data Index: 7380255 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.3793. Min Act: -0.1700
Data Index: 6464870 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.3793. Min Act: -0.1700
Data Index: 4911721 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.3480. Min Act: -0.1700
Data Index: 8170427 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.3168. Min Act: -0.1700
Data Index: 5701182 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2543. Min Act: -0.1700
Data Index: 1535300 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2855. Min Act: -0.1700
Data Index: 3740706 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2855. Min Act: -0.1700
Data Index: 4913512 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2855. Min Act: -0.1700
Data Index: 1838642 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2855. Min Act: -0.1700
Data Index: 4985638 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2543. Min Act: -0.1700
Data Index: 3662326 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2230. Min Act: -0.1700
Data Index: 7635995 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2230. Min Act: -0.1699
Data Index: 3665274 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1935704 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5980. Min Range: -6.5980
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7396494 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19