Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1497. Min Range: -6.1497
Max Act: 6.1497. Min Act: -0.1700
Data Index: 6599037 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1497. Min Range: -6.1497
Max Act: 6.0872. Min Act: -0.1700
Data Index: 6781852 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.9935. Min Act: -0.1700
Data Index: 5300664 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8997. Min Act: -0.1700
Data Index: 3029151 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8685. Min Act: -0.1700
Data Index: 5796859 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8685. Min Act: -0.1700
Data Index: 4642846 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8372. Min Act: -0.1700
Data Index: 3492965 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8060. Min Act: -0.1700
Data Index: 2168743 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8372. Min Act: -0.1700
Data Index: 6342045 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8372. Min Act: -0.1700
Data Index: 3364167 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8372. Min Act: -0.1700
Data Index: 412895 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8060. Min Act: -0.1700
Data Index: 6230031 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8060. Min Act: -0.1700
Data Index: 6701908 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.8060. Min Act: -0.1700
Data Index: 3646496 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.7747. Min Act: -0.1700
Data Index: 6289299 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.7435. Min Act: -0.1700
Data Index: 6599502 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.7747. Min Act: -0.1700
Data Index: 6623050 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.7747. Min Act: -0.1700
Data Index: 1006017 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.7747. Min Act: -0.1700
Data Index: 5556394 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1497. Min Range: -6.1497
Max Act: 5.7435. Min Act: -0.1700
Data Index: 6730246 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19