Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.3003. Min Act: -0.1700
Data Index: 8823953 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.2690. Min Act: -0.1700
Data Index: 7371459 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.1440. Min Act: -0.1700
Data Index: 2618928 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.1440. Min Act: -0.1700
Data Index: 5380238 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.1128. Min Act: -0.1700
Data Index: 3104590 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0815. Min Act: -0.1700
Data Index: 6979919 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0815. Min Act: -0.1700
Data Index: 4845897 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0815. Min Act: -0.1700
Data Index: 4399078 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0502. Min Act: -0.1700
Data Index: 6402905 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0502. Min Act: -0.1700
Data Index: 5114188 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0502. Min Act: -0.1700
Data Index: 8058246 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0502. Min Act: -0.1700
Data Index: 4066057 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0190. Min Act: -0.1700
Data Index: 3633872 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0190. Min Act: -0.1700
Data Index: 2254637 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3003. Min Range: -4.3003
Max Act: 4.0190. Min Act: -0.1700
Data Index: 8545529 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3003. Min Range: -4.3003
Max Act: 3.9565. Min Act: -0.1700
Data Index: 7621099 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3003. Min Range: -4.3003
Max Act: 3.9565. Min Act: -0.1700
Data Index: 3637282 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3003. Min Range: -4.3003
Max Act: 3.9877. Min Act: -0.1700
Data Index: 8644372 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3003. Min Range: -4.3003
Max Act: 3.9252. Min Act: -0.1700
Data Index: 8681744 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3003. Min Range: -4.3003
Max Act: 3.9565. Min Act: -0.1700
Data Index: 4715617 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19