Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1107. Min Range: -5.1107
Max Act: 5.1107. Min Act: -0.1700
Data Index: 951723 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1107. Min Range: -5.1107
Max Act: 5.0795. Min Act: -0.1700
Data Index: 7079030 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1107. Min Range: -5.1107
Max Act: 5.0170. Min Act: -0.1700
Data Index: 5411864 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1107. Min Range: -5.1107
Max Act: 5.0170. Min Act: -0.1700
Data Index: 518306 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1107. Min Range: -5.1107
Max Act: 5.0170. Min Act: -0.1700
Data Index: 6402502 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.9857. Min Act: -0.1700
Data Index: 2667800 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.9545. Min Act: -0.1700
Data Index: 6647756 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.9545. Min Act: -0.1700
Data Index: 1254995 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6350022 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.9232. Min Act: -0.1700
Data Index: 215721 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8920. Min Act: -0.1700
Data Index: 4103004 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8920. Min Act: -0.1700
Data Index: 8013095 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8607. Min Act: -0.1700
Data Index: 6724615 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8607. Min Act: -0.1700
Data Index: 7803647 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8295. Min Act: -0.1700
Data Index: 6010669 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8295. Min Act: -0.1700
Data Index: 864041 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8295. Min Act: -0.1700
Data Index: 1128774 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8295. Min Act: -0.1700
Data Index: 861675 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.8295. Min Act: -0.1700
Data Index: 2282649 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1107. Min Range: -5.1107
Max Act: 4.7982. Min Act: -0.1700
Data Index: 3757660 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19