Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1259. Min Range: -7.1259
Max Act: 7.1259. Min Act: -0.1700
Data Index: 8436666 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.8759. Min Act: -0.1700
Data Index: 1376952 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.8134. Min Act: -0.1700
Data Index: 4119838 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.6259. Min Act: -0.1700
Data Index: 7438752 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.5321. Min Act: -0.1700
Data Index: 5092520 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.5634. Min Act: -0.1700
Data Index: 7521838 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.4696. Min Act: -0.1700
Data Index: 1998596 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.4384. Min Act: -0.1700
Data Index: 286824 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.4696. Min Act: -0.1700
Data Index: 389314 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.4071. Min Act: -0.1700
Data Index: 1509173 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.3759. Min Act: -0.1700
Data Index: 3687575 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.4071. Min Act: -0.1700
Data Index: 7901259 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.3759. Min Act: -0.1700
Data Index: 4775249 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.3759. Min Act: -0.1700
Data Index: 4059419 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.3446. Min Act: -0.1700
Data Index: 4097862 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.2821. Min Act: -0.1700
Data Index: 7319729 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.3446. Min Act: -0.1700
Data Index: 7782454 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.3134. Min Act: -0.1700
Data Index: 1894352 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.2821. Min Act: -0.1700
Data Index: 4746195 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1259. Min Range: -7.1259
Max Act: 6.2821. Min Act: -0.1700
Data Index: 1009033 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19