Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 707 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.0902. Min Range: -4.0902
Max Act: 4.0902. Min Act: -0.1700
Data Index: 3077015 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.9339. Min Act: -0.1700
Data Index: 1922498 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.9026. Min Act: -0.1700
Data Index: 2190782 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.8557. Min Act: -0.1700
Data Index: 4982911 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.8401. Min Act: -0.1700
Data Index: 7616616 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.8245. Min Act: -0.1700
Data Index: 6484056 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7776. Min Act: -0.1700
Data Index: 6711658 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7932. Min Act: -0.1700
Data Index: 6666549 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7776. Min Act: -0.1700
Data Index: 6711664 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7776. Min Act: -0.1700
Data Index: 100535 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7776. Min Act: -0.1700
Data Index: 2501780 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7463. Min Act: -0.1700
Data Index: 1133454 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7463. Min Act: -0.1700
Data Index: 1051843 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7306. Min Act: -0.1700
Data Index: 2527979 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7306. Min Act: -0.1700
Data Index: 4026632 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.6994. Min Act: -0.1700
Data Index: 3699609 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7150. Min Act: -0.1700
Data Index: 1063389 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.6837. Min Act: -0.1700
Data Index: 4625729 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.7150. Min Act: -0.1700
Data Index: 7181598 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0902. Min Range: -4.0902
Max Act: 3.6994. Min Act: -0.1700
Data Index: 5387193 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19