Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0364. Min Range: -7.0364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 2547792 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.9427. Min Act: -0.1700
Data Index: 4885026 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8177. Min Act: -0.1700
Data Index: 3896135 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.7552. Min Act: -0.1700
Data Index: 1965106 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.6927. Min Act: -0.1700
Data Index: 2366586 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.6302. Min Act: -0.1700
Data Index: 3336693 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.5052. Min Act: -0.1700
Data Index: 1300289 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.5052. Min Act: -0.1700
Data Index: 8317798 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.4427. Min Act: -0.1700
Data Index: 8504927 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.4114. Min Act: -0.1700
Data Index: 3490285 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.4114. Min Act: -0.1700
Data Index: 3732573 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.3802. Min Act: -0.1700
Data Index: 3763839 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.4114. Min Act: -0.1700
Data Index: 3296385 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.4114. Min Act: -0.1700
Data Index: 2151932 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.3802. Min Act: -0.1700
Data Index: 3815718 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.3802. Min Act: -0.1700
Data Index: 8505427 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.3802. Min Act: -0.1700
Data Index: 7424261 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.3802. Min Act: -0.1700
Data Index: 7403006 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.3489. Min Act: -0.1700
Data Index: 3881402 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.3489. Min Act: -0.1700
Data Index: 7424259 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19