Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4387 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.1258. Min Act: -0.1700
Data Index: 5057944 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0945. Min Act: -0.1700
Data Index: 8800533 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0633. Min Act: -0.1700
Data Index: 400166 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0008. Min Act: -0.1700
Data Index: 888961 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.9383. Min Act: -0.1700
Data Index: 400164 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.9070. Min Act: -0.1700
Data Index: 2643337 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.9070. Min Act: -0.1700
Data Index: 571392 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8758. Min Act: -0.1700
Data Index: 6385422 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 7805889 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 6789297 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 4214386 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2691050 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8133. Min Act: -0.1700
Data Index: 327998 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8758. Min Act: -0.1700
Data Index: 4036777 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 7129678 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8133. Min Act: -0.1700
Data Index: 2808470 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8133. Min Act: -0.1700
Data Index: 8379411 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8133. Min Act: -0.1700
Data Index: 571386 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 5871748 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7508. Min Act: -0.1700
Data Index: 4376935 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19