Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2303 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0772. Min Range: -8.0772
Max Act: 8.0772. Min Act: -0.1700
Data Index: 5560068 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0772. Min Range: -8.0772
Max Act: 8.0460. Min Act: -0.1700
Data Index: 7475559 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.7647. Min Act: -0.1700
Data Index: 2881268 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.7022. Min Act: -0.1700
Data Index: 130791 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.5772. Min Act: -0.1700
Data Index: 7122065 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.5460. Min Act: -0.1700
Data Index: 5275217 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.5147. Min Act: -0.1700
Data Index: 3073752 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.4835. Min Act: -0.1700
Data Index: 7990446 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.3897. Min Act: -0.1700
Data Index: 4457849 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.3897. Min Act: -0.1700
Data Index: 3059266 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.3272. Min Act: -0.1700
Data Index: 7568156 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.3272. Min Act: -0.1700
Data Index: 223254 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.3272. Min Act: -0.1700
Data Index: 2178948 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.2960. Min Act: -0.1700
Data Index: 4626138 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.2960. Min Act: -0.1700
Data Index: 7116296 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.2647. Min Act: -0.1700
Data Index: 1754524 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.2647. Min Act: -0.1700
Data Index: 283174 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.2647. Min Act: -0.1700
Data Index: 7430825 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.2335. Min Act: -0.1700
Data Index: 2865729 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0772. Min Range: -8.0772
Max Act: 7.2335. Min Act: -0.1700
Data Index: 260175 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19