Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.8943. Min Act: -0.1700
Data Index: 7843997 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.8006. Min Act: -0.1700
Data Index: 6036324 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.7068. Min Act: -0.1700
Data Index: 526990 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.7068. Min Act: -0.1700
Data Index: 905612 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6909457 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.6756. Min Act: -0.1700
Data Index: 5745292 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.6756. Min Act: -0.1700
Data Index: 741932 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.6443. Min Act: -0.1700
Data Index: 6725367 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.6443. Min Act: -0.1700
Data Index: 8325398 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5818. Min Act: -0.1700
Data Index: 3867290 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5818. Min Act: -0.1700
Data Index: 2323137 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5818. Min Act: -0.1700
Data Index: 1356630 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5506. Min Act: -0.1700
Data Index: 8434889 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4153130 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5193. Min Act: -0.1700
Data Index: 1255308 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.4881. Min Act: -0.1700
Data Index: 2690566 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5193. Min Act: -0.1700
Data Index: 7856255 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.4881. Min Act: -0.1700
Data Index: 1028028 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5193. Min Act: -0.1700
Data Index: 1395610 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8943. Min Range: -4.8943
Max Act: 4.5193. Min Act: -0.1700
Data Index: 1726952 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19