Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2138. Min Range: -7.2138
Max Act: 7.2138. Min Act: -0.1700
Data Index: 8301573 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.9950. Min Act: -0.1700
Data Index: 8795988 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.9950. Min Act: -0.1700
Data Index: 277434 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.9013. Min Act: -0.1700
Data Index: 1691429 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.8700. Min Act: -0.1700
Data Index: 6127528 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.9325. Min Act: -0.1700
Data Index: 1516332 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.8388. Min Act: -0.1700
Data Index: 4204720 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.8700. Min Act: -0.1700
Data Index: 1323647 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.8388. Min Act: -0.1700
Data Index: 4815024 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.8075. Min Act: -0.1700
Data Index: 1178984 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.7763. Min Act: -0.1700
Data Index: 6218419 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.6825. Min Act: -0.1700
Data Index: 4169589 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.8075. Min Act: -0.1700
Data Index: 6275118 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.7763. Min Act: -0.1700
Data Index: 5504455 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.7763. Min Act: -0.1700
Data Index: 1935196 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.7450. Min Act: -0.1700
Data Index: 866950 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.7763. Min Act: -0.1700
Data Index: 1323650 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.7763. Min Act: -0.1700
Data Index: 5504458 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.7138. Min Act: -0.1700
Data Index: 8795990 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2138. Min Range: -7.2138
Max Act: 6.6513. Min Act: -0.1700
Data Index: 3348465 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19