Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.9998. Min Act: -0.1700
Data Index: 2645276 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.8748. Min Act: -0.1700
Data Index: 7820902 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.8748. Min Act: -0.1700
Data Index: 8737866 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.7498. Min Act: -0.1700
Data Index: 3219505 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.7498. Min Act: -0.1699
Data Index: 6557902 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.6873. Min Act: -0.1700
Data Index: 7122445 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.6873. Min Act: -0.1700
Data Index: 4377202 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5936. Min Act: -0.1700
Data Index: 1746450 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.6561. Min Act: -0.1700
Data Index: 8453983 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5936. Min Act: -0.1700
Data Index: 1961789 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5936. Min Act: -0.1700
Data Index: 5472295 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.6248. Min Act: -0.1700
Data Index: 8452271 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5936. Min Act: -0.1700
Data Index: 3500221 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5623. Min Act: -0.1700
Data Index: 3430865 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5311. Min Act: -0.1699
Data Index: 8552467 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5311. Min Act: -0.1700
Data Index: 4028547 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5623. Min Act: -0.1700
Data Index: 4463279 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.4998. Min Act: -0.1700
Data Index: 6557905 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.5311. Min Act: -0.1700
Data Index: 2645279 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9998. Min Range: -7.9998
Max Act: 7.4686. Min Act: -0.1700
Data Index: 7244308 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19