Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 116 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.8567. Min Act: -0.1700
Data Index: 1219529 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.7630. Min Act: -0.1700
Data Index: 738745 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.7630. Min Act: -0.1700
Data Index: 5929254 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.7317. Min Act: -0.1700
Data Index: 7520521 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6380. Min Act: -0.1700
Data Index: 7269494 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.7005. Min Act: -0.1700
Data Index: 4033518 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6067. Min Act: -0.1700
Data Index: 8582290 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6380. Min Act: -0.1700
Data Index: 4415356 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.6067. Min Act: -0.1700
Data Index: 7876163 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 867035 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5130. Min Act: -0.1700
Data Index: 2684940 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5130. Min Act: -0.1700
Data Index: 8745951 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5130. Min Act: -0.1700
Data Index: 5687361 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.5442. Min Act: -0.1700
Data Index: 8606066 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.4817. Min Act: -0.1700
Data Index: 2735303 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.4817. Min Act: -0.1700
Data Index: 5018361 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.4505. Min Act: -0.1700
Data Index: 1208075 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.4505. Min Act: -0.1700
Data Index: 4925047 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.4192. Min Act: -0.1700
Data Index: 6702808 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8567. Min Range: -5.8567
Max Act: 5.4505. Min Act: -0.1700
Data Index: 8764905 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19