Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.9320. Min Act: -0.1700
Data Index: 7481138 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.6195. Min Act: -0.1700
Data Index: 2462650 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.6507. Min Act: -0.1700
Data Index: 3452213 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.6507. Min Act: -0.1700
Data Index: 7188857 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.5882. Min Act: -0.1700
Data Index: 2589826 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.5882. Min Act: -0.1700
Data Index: 5793149 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.5570. Min Act: -0.1700
Data Index: 7826070 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.5570. Min Act: -0.1700
Data Index: 4312111 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.4945. Min Act: -0.1700
Data Index: 6351119 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.4945. Min Act: -0.1700
Data Index: 87558 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.4632. Min Act: -0.1700
Data Index: 8189943 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.4632. Min Act: -0.1700
Data Index: 1681411 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.4320. Min Act: -0.1700
Data Index: 355557 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.4007. Min Act: -0.1700
Data Index: 6661646 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.3695. Min Act: -0.1700
Data Index: 5368762 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.3695. Min Act: -0.1700
Data Index: 1966888 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.3695. Min Act: -0.1700
Data Index: 7115857 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.3382. Min Act: -0.1700
Data Index: 5211539 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.3382. Min Act: -0.1700
Data Index: 163547 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9320. Min Range: -5.9320
Max Act: 5.3070. Min Act: -0.1700
Data Index: 4795537 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19